This proposal is developing a framework for deploying and interacting with AI models onchain using Arbitrum Stylus and Rust. This initiative will unlock innovative use cases for the Arbitrum ecosystem, such as decentralized AI computation and verifiable machine learning, while showcasing the scalability and efficiency of Stylus. By focusing heavily on development resources and open-source contributions, this project aims to establish Arbitrum as a hub for decentralized AI applications.
The idea for this proposal emerged from a grassroots conversation within the Arbitrum communities. A Twitter thread sparked by Patrick McCorry's observations on the EthGlobal hackathon led to a comment by Matt Hamilton (Senior DevRel at Arbitrum) suggesting embedding AI neural networks in NFTs using Stylus. Inspired by this, I conducted an experiment deploying a decision tree model using Stylus and Rust, which proved functional but highlighted challenges.
Having previously and currently contributing to the Stylus ecosystem through the @stylusdev Twitter account, where I create developer education content, I am passionate about pushing Stylus’s capabilities and onboarding developers. This proposal is the next logical step in realizing Stylus's potential by addressing existing limitations and building tools to make onchain AI a reality.
The motivation is clear: onchain AI models represent a groundbreaking use case for blockchain technology, enabling trustless, verifiable, and decentralized computation for industries such as finance, gaming, and governance.
This proposal aligns closely with the Arbitrum DAO’s mission and guiding values:
As a Rust developer with deep experience in Stylus, I have already laid the groundwork for this initiative. The project will also leverage the expertise of two ML engineers and another Rust engineer to ensure scalability and successful delivery.
Justification: Training AI models, even lightweight ones, can be computationally intensive and require significant resources to achieve reasonable training times and performance.
Justification: High-quality data is crucial for training effective AI models. Costs cover acquisition and preparation to ensure models are trained on reliable data.
Justification: Specialized tools can significantly enhance development efficiency, model performance, and security, justifying their cost.
Justification: Security is paramount, especially when deploying onchain. Audits help prevent costly exploits and build trust with users and the community.
Justification: Ongoing research is essential to push the boundaries of what's possible and to incorporate the latest advancements into the project.
Justification: Robust testing and deployment processes ensure reliability and facilitate smooth integration and updates.
Justification: Comprehensive documentation and support tools are vital for community adoption and to lower the barrier to entry for new developers.
Justification: Proper legal groundwork prevents future disputes and ensures the project adheres to all regulations and best practices.
Justification: A contingency fund ensures the project can handle unexpected challenges without compromising its goals.
This proposal is an opportunity to push the boundaries of what blockchain technology can achieve by enabling decentralized AI computation on Arbitrum Stylus. By combining a solid technical foundation, community engagement, and a passion for innovation, we aim to make Arbitrum the go-to ecosystem for onchain AI applications.
This proposal is developing a framework for deploying and interacting with AI models onchain using Arbitrum Stylus and Rust. This initiative will unlock innovative use cases for the Arbitrum ecosystem, such as decentralized AI computation and verifiable machine learning, while showcasing the scalability and efficiency of Stylus. By focusing heavily on development resources and open-source contributions, this project aims to establish Arbitrum as a hub for decentralized AI applications.
The idea for this proposal emerged from a grassroots conversation within the Arbitrum communities. A Twitter thread sparked by Patrick McCorry's observations on the EthGlobal hackathon led to a comment by Matt Hamilton (Senior DevRel at Arbitrum) suggesting embedding AI neural networks in NFTs using Stylus. Inspired by this, I conducted an experiment deploying a decision tree model using Stylus and Rust, which proved functional but highlighted challenges.
Having previously and currently contributing to the Stylus ecosystem through the @stylusdev Twitter account, where I create developer education content, I am passionate about pushing Stylus’s capabilities and onboarding developers. This proposal is the next logical step in realizing Stylus's potential by addressing existing limitations and building tools to make onchain AI a reality.
The motivation is clear: onchain AI models represent a groundbreaking use case for blockchain technology, enabling trustless, verifiable, and decentralized computation for industries such as finance, gaming, and governance.
This proposal aligns closely with the Arbitrum DAO’s mission and guiding values:
As a Rust developer with deep experience in Stylus, I have already laid the groundwork for this initiative. The project will also leverage the expertise of two ML engineers and another Rust engineer to ensure scalability and successful delivery.
Justification: Training AI models, even lightweight ones, can be computationally intensive and require significant resources to achieve reasonable training times and performance.
Justification: High-quality data is crucial for training effective AI models. Costs cover acquisition and preparation to ensure models are trained on reliable data.
Justification: Specialized tools can significantly enhance development efficiency, model performance, and security, justifying their cost.
Justification: Security is paramount, especially when deploying onchain. Audits help prevent costly exploits and build trust with users and the community.
Justification: Ongoing research is essential to push the boundaries of what's possible and to incorporate the latest advancements into the project.
Justification: Robust testing and deployment processes ensure reliability and facilitate smooth integration and updates.
Justification: Comprehensive documentation and support tools are vital for community adoption and to lower the barrier to entry for new developers.
Justification: Proper legal groundwork prevents future disputes and ensures the project adheres to all regulations and best practices.
Justification: A contingency fund ensures the project can handle unexpected challenges without compromising its goals.
This proposal is an opportunity to push the boundaries of what blockchain technology can achieve by enabling decentralized AI computation on Arbitrum Stylus. By combining a solid technical foundation, community engagement, and a passion for innovation, we aim to make Arbitrum the go-to ecosystem for onchain AI applications.
As Stylus is a key competitive advantage for Arbitrum, I think the DAO should encourage initiatives leveraging it. Because of this, I am happy to see this proposal.
Generally, I am supportive of it. But, I'd like to ask a clarification on funding. Do you expect to seek funding from other places as well or would this be funded by Arbitrum DAO only? For example, the Arbitrum Foundation has recently launched the Trailblazer grant program, specifically focused on powering AI innovation on Arbitrum. This project might be a good fit for it.
As Stylus is a key competitive advantage for Arbitrum, I think the DAO should encourage initiatives leveraging it. Because of this, I am happy to see this proposal.
Generally, I am supportive of it. But, I'd like to ask a clarification on funding. Do you expect to seek funding from other places as well or would this be funded by Arbitrum DAO only? For example, the Arbitrum Foundation has recently launched the Trailblazer grant program, specifically focused on powering AI innovation on Arbitrum. This project might be a good fit for it.
I’ve seen the Trailblazer AI Grant Program, and it’s a fantastic initiative for supporting AI projects within the community. However, the program has a cap of $10,000 per project, which isn’t sufficient for the scale of our proposal.
I’ve seen the Trailblazer AI Grant Program, and it’s a fantastic initiative for supporting AI projects within the community. However, the program has a cap of $10,000 per project, which isn’t sufficient for the scale of our proposal.
Even if the amount is small, i request you to apply for it so we know that you have passed some basic level of vetting.
Ideally, I would be more comfortable voting for this proposal and the larger amounts if you have already got $10k from the AF and passed their basic screening. Otherwise, I find it hard to trust a team with $200k based on little prior information except a Twitter account that posts about stylus. Even if the idea is good, why are you the best one to implement it?
We completely understand your concerns, and we appreciate your honesty. We're open to receiving funds in stages—only upon the completion of each milestone. This way, we would receive funding after delivering the agreed-upon results, ensuring accountability and creating a win-win situation for everyone.
we will be hiring new team members to bring this project to life, we'll be transparent about who is involved as we build the team. We believe that by showing our commitment and being open about our team and progress, we can build the trust needed to move forward.
Thank you for your feedback. We're dedicated to making this project a success and are eager to work together to achieve our shared goals.
Thank you for highlighting this important aspect! Yes, we absolutely plan to publish the results on the forum to keep the community informed. We'll provide monthly updates throughout the project to share our progress, achievements, and any challenges we encounter.
Thank you for highlighting this important aspect! Yes, we absolutely plan to publish the results on the forum to keep the community informed. We'll provide monthly updates throughout the project to share our progress, achievements, and any challenges we encounter.
Upon completion, we'll release a comprehensive final report detailing the outcomes and insights gained from the project. We're also open to conducting a final evaluation a few months after completion to assess the success and impact of our work.
Regular communication is crucial, and we value the community's involvement every step of the way.
Conduct a detailed study on the scalability of Stylus for AI models.
Conduct a detailed study on the scalability of Stylus for AI models.
We’re interested in learning more about the approach planned for this study. Could you share the specific methodologies or key factors you plan to analyze during this phase? Understanding these details would help clarify how this phase will inform the project’s next steps.
Absolutely! below is our approach for the scalability study of Stylus for AI models.
Methodology:
Key Factors We'll Analyze:
How This Phase Informs Next Steps:
How do you propose we approach this? Additionally, how does this fit into the competitive landscape, especially considering that other L2s (example Mode Network) are significantly shifting their narrative toward AI agents?
How do you propose we approach this? Additionally, how does this fit into the competitive landscape, especially considering that other L2s (example Mode Network) are significantly shifting their narrative toward AI agents?
Thank you for your thoughtful feedback! I completely agree that the real measure of success will be in attracting developers to build and deploy AI models on this infrastructure. To achieve this, we plan to implement a robust outreach and engagement strategy:
Regarding the competitive landscape, we're aware that other L2s like Mode Network are shifting toward AI agents. However, we believe that Arbitrum's unique capabilities with Stylus and the ability to use Rust give us a significant advantage. Our focus is on creating a developer-friendly environment that offers efficiency and scalability for on-chain AI applications.
By proactively engaging with the developer community and highlighting the strengths of Arbitrum, we aim to position it as the go-to platform for on-chain AI. We're excited about the potential and are committed to fostering an ecosystem where innovation thrives.
Thanks again for your input!
The project will release open-source tools and developer education materials to empower the broader Arbitrum community.
Additionally, is there room for budget optimization? For example, the costs for cloud computing and data collection could potentially be reduced by seeking community collaboration, such as partnering with existing Arbitrum projects to share resources and expenses.
Additionally, is there room for budget optimization? For example, the costs for cloud computing and data collection could potentially be reduced by seeking community collaboration, such as partnering with existing Arbitrum projects to share resources and expenses.
That's a great point! While we hadn't initially thought about optimizing the budget through community collaborations, we're definitely open to it. We'd love to connect with others in the Arbitrum ecosystem who can help share resources like cloud computing and data collection. If we can establish these partnerships, we can certainly reduce costs. If you can help with this or know anyone who might be interested, we'd really appreciate it!
We appreciate your attention to these points to strengthen the proposal.
In the first phase, you mentioned testing Stylus’ scalability for AI models. If performance or compatibility bottlenecks are discovered, how will the project be adjusted?
In the third phase, you plan to optimize the framework and support more complex models within just two months. Isn’t that timeframe too short? Do you have a contingency plan to handle potential delays?
If we find bottlenecks in Phase 1:
Thank you for pointing that out! You're absolutely correct. We'll update the proposal to reflect the budget in ARB . We appreciate your attention to detail and are making that adjustment right away. Thanks again for your support!
Release of open-source tools and libraries for the community.
Also, would you consider offering developer bounties or hosting competitions to encourage early adoption? We believe incentivizing innovative use cases could rapidly grow the pool of Stylus-based projects.
Also, would you consider offering developer bounties or hosting competitions to encourage early adoption? We believe incentivizing innovative use cases could rapidly grow the pool of Stylus-based projects.
Great idea! Yes, we're definitely considering offering developer bounties and hosting competitions to encourage early adoption. Considering partnering with the multiple grants teams in the ecosystem. We believe that incentivizing innovative use cases is a fantastic way to rapidly grow the pool of Stylus-based projects. We're excited to support and collaborate with developers who are pushing the boundaries of what's possible.
I’ve seen the Trailblazer AI Grant Program, and it’s a fantastic initiative for supporting AI projects within the community. However, the program has a cap of $10,000 per project, which isn’t sufficient for the scale of our proposal.
I’ve seen the Trailblazer AI Grant Program, and it’s a fantastic initiative for supporting AI projects within the community. However, the program has a cap of $10,000 per project, which isn’t sufficient for the scale of our proposal.
Even if the amount is small, i request you to apply for it so we know that you have passed some basic level of vetting.
Ideally, I would be more comfortable voting for this proposal and the larger amounts if you have already got $10k from the AF and passed their basic screening. Otherwise, I find it hard to trust a team with $200k based on little prior information except a Twitter account that posts about stylus. Even if the idea is good, why are you the best one to implement it?
We completely understand your concerns, and we appreciate your honesty. We're open to receiving funds in stages—only upon the completion of each milestone. This way, we would receive funding after delivering the agreed-upon results, ensuring accountability and creating a win-win situation for everyone.
we will be hiring new team members to bring this project to life, we'll be transparent about who is involved as we build the team. We believe that by showing our commitment and being open about our team and progress, we can build the trust needed to move forward.
Thank you for your feedback. We're dedicated to making this project a success and are eager to work together to achieve our shared goals.
Thank you for highlighting this important aspect! Yes, we absolutely plan to publish the results on the forum to keep the community informed. We'll provide monthly updates throughout the project to share our progress, achievements, and any challenges we encounter.
Thank you for highlighting this important aspect! Yes, we absolutely plan to publish the results on the forum to keep the community informed. We'll provide monthly updates throughout the project to share our progress, achievements, and any challenges we encounter.
Upon completion, we'll release a comprehensive final report detailing the outcomes and insights gained from the project. We're also open to conducting a final evaluation a few months after completion to assess the success and impact of our work.
Regular communication is crucial, and we value the community's involvement every step of the way.
Conduct a detailed study on the scalability of Stylus for AI models.
Conduct a detailed study on the scalability of Stylus for AI models.
We’re interested in learning more about the approach planned for this study. Could you share the specific methodologies or key factors you plan to analyze during this phase? Understanding these details would help clarify how this phase will inform the project’s next steps.
Absolutely! below is our approach for the scalability study of Stylus for AI models.
Methodology:
Key Factors We'll Analyze:
How This Phase Informs Next Steps:
How do you propose we approach this? Additionally, how does this fit into the competitive landscape, especially considering that other L2s (example Mode Network) are significantly shifting their narrative toward AI agents?
How do you propose we approach this? Additionally, how does this fit into the competitive landscape, especially considering that other L2s (example Mode Network) are significantly shifting their narrative toward AI agents?
Thank you for your thoughtful feedback! I completely agree that the real measure of success will be in attracting developers to build and deploy AI models on this infrastructure. To achieve this, we plan to implement a robust outreach and engagement strategy:
Regarding the competitive landscape, we're aware that other L2s like Mode Network are shifting toward AI agents. However, we believe that Arbitrum's unique capabilities with Stylus and the ability to use Rust give us a significant advantage. Our focus is on creating a developer-friendly environment that offers efficiency and scalability for on-chain AI applications.
By proactively engaging with the developer community and highlighting the strengths of Arbitrum, we aim to position it as the go-to platform for on-chain AI. We're excited about the potential and are committed to fostering an ecosystem where innovation thrives.
Thanks again for your input!
The project will release open-source tools and developer education materials to empower the broader Arbitrum community.
Additionally, is there room for budget optimization? For example, the costs for cloud computing and data collection could potentially be reduced by seeking community collaboration, such as partnering with existing Arbitrum projects to share resources and expenses.
Additionally, is there room for budget optimization? For example, the costs for cloud computing and data collection could potentially be reduced by seeking community collaboration, such as partnering with existing Arbitrum projects to share resources and expenses.
That's a great point! While we hadn't initially thought about optimizing the budget through community collaborations, we're definitely open to it. We'd love to connect with others in the Arbitrum ecosystem who can help share resources like cloud computing and data collection. If we can establish these partnerships, we can certainly reduce costs. If you can help with this or know anyone who might be interested, we'd really appreciate it!
We appreciate your attention to these points to strengthen the proposal.
In the first phase, you mentioned testing Stylus’ scalability for AI models. If performance or compatibility bottlenecks are discovered, how will the project be adjusted?
In the third phase, you plan to optimize the framework and support more complex models within just two months. Isn’t that timeframe too short? Do you have a contingency plan to handle potential delays?
If we find bottlenecks in Phase 1:
Thank you for pointing that out! You're absolutely correct. We'll update the proposal to reflect the budget in ARB . We appreciate your attention to detail and are making that adjustment right away. Thanks again for your support!
Release of open-source tools and libraries for the community.
Also, would you consider offering developer bounties or hosting competitions to encourage early adoption? We believe incentivizing innovative use cases could rapidly grow the pool of Stylus-based projects.
Also, would you consider offering developer bounties or hosting competitions to encourage early adoption? We believe incentivizing innovative use cases could rapidly grow the pool of Stylus-based projects.
Great idea! Yes, we're definitely considering offering developer bounties and hosting competitions to encourage early adoption. Considering partnering with the multiple grants teams in the ecosystem. We believe that incentivizing innovative use cases is a fantastic way to rapidly grow the pool of Stylus-based projects. We're excited to support and collaborate with developers who are pushing the boundaries of what's possible.
The project will release open-source tools and developer education materials to empower the broader Arbitrum community.
The emphasis on open-source tools and developer education demonstrates a strong commitment to community building. Have you considered creating beginner-friendly templates, example projects, or a flow to lower the entry barrier for developers unfamiliar with AI or Rust?
Hello, thanks for your great input on the proposal.
Absolutely! We totally get that not everyone is familiar with AI or Rust. We're planning to create beginner-friendly templates and example projects to help developers get started quickly. Our goal is to lower the entry barrier and make it easy for anyone to dive in, even if they're new to these technologies. We'll provide step-by-step guides and resources to support developers of all skill levels.
We appreciate your attention to these points to strengthen the proposal.
Thank you for catching that error in the timeline! We'll adjust the proposal to reflect this.
We'll ensure all dates align correctly with the voting schedule. Thank you again for your attention to detail. we appreciate your help in strengthening the proposal!
In the first phase, you mentioned testing Stylus’ scalability for AI models. If performance or compatibility bottlenecks are discovered, how will the project be adjusted?
In the third phase, you plan to optimize the framework and support more complex models within just two months. Isn’t that timeframe too short? Do you have a contingency plan to handle potential delays?
If we find bottlenecks in Phase 1:
If we run into performance or compatibility issues, we'll adapt our approach. This might mean optimizing our models, tweaking the code, or exploring alternative solutions to overcome the challenges. Our goal is to ensure the project remains valuable and feasible, so we're prepared to adjust as needed.
You're right; two months is ambitious for optimizing complex models. We have contingency plans in place. If we need more time to maintain quality, we'll adjust the schedule. Our priority is to deliver a robust framework, even if it means extending the timeline a bit. We also have buffer times included in our time frame.
Really appreciate your insights! We're committed to making this project a success.
Thank you for your thoughtful feedback and for seeing the potential benefits of the proposal for the DAO. I appreciate your observations.
Regarding your question about timelines and budget: If we find that we cannot meet the proposed timelines, we are committed to completing the project within the same budget. We will not request additional funding. Instead, we'll adjust our approach and allocate our resources efficiently to ensure we deliver the promised outcomes.
Our priority is to responsibly manage the resources provided and to maintain transparency with the DAO throughout the project's execution. If any delays or significant changes arise, we'll promptly communicate them to keep everyone informed and to discuss the best way forward.
I'm confident that with careful planning and open communication, we'll successfully execute the proposal.
you could add more specific metrics… such as the number of active developers or projects adopting your framework within a given timeframe
Great question! We definitely plan to measure success with specific metrics. Besides releasing the open-source tools and libraries, we'll be tracking:
Additionally, if community developers want to build upon this project, do you have any incentive plans, such as hosting hackathons or offering grant rewards?”
Additionally, if community developers want to build upon this project, do you have any incentive plans, such as hosting hackathons or offering grant rewards?”
Absolutely! We plan to actively encourage and support community developers who want to build on our project. Hosting hackathons is definitely on our agenda to foster innovation and collaboration. We're also looking into collaborating with grants teams in the ecosystem or offering rewards for standout projects that utilize our framework. Our aim is to create a vibrant ecosystem around on-chain AI, and empowering developers is a big part of that. We're excited to see the amazing things the community will create!
The direction of on-chain AI is indeed cutting-edge, but given the current high demand for DeFi and gaming on-chain applications, does your choice of on-chain AI models have specific use cases to support it? For instance, what scenarios could your decision tree model be practically applied to?
The direction of on-chain AI is indeed cutting-edge, but given the current high demand for DeFi and gaming on-chain applications, does your choice of on-chain AI models have specific use cases to support it? For instance, what scenarios could your decision tree model be practically applied to?
Great question! Absolutely, our on-chain AI models have specific use cases in both DeFi and gaming.
In DeFi, a decision tree model can be used for on-chain credit scoring. For example, it can analyze a user's transaction history, asset holdings, and interaction patterns to assess creditworthiness. This allows decentralized lending platforms to make smarter lending decisions without relying on off-chain data, enhancing trust and efficiency in lending protocols.
In gaming, decision trees can drive dynamic in-game events or NPC behaviors. For instance, in a blockchain-based game, the model could determine outcomes based on player choices, such as unlocking special quests or adapting enemy strategies. This adds a layer of complexity and personalization that enhances the gaming experience.
By deploying these models on-chain, we ensure transparency and trust in the decision-making process, which is crucial for decentralized applications.
The project will release open-source tools and developer education materials to empower the broader Arbitrum community.
The project will release open-source tools and developer education materials to empower the broader Arbitrum community.
This is key to success. But have you considered more proactive strategies to engage the community? Virtual hackathons, rewards for projects using your framework, or collaborations with prominent developers could be excellent ways to increase adoption and the project’s impact.
Yes, absolutely! We plan to engage in developer partnerships and host hackathons, especially after completing the first iteration of our initiative. Right now, our main focus is on bringing the framework to reality. Once it's established, we'll actively encourage developers to build applications leveraging the infrastructure we've created. Community engagement is entirely in our plan, and we're excited to foster innovation within the Arbitrum ecosystem.
Given the timeline and estimated budget, how do you plan to handle the complexity and cost this entails? Perhaps you could clarify whether this will be an initial implementation or just a research stage within the project. This would help to structure the phases.
Our plan is to initially focus on research and feasibility during the early phases of the project. This means we'll explore how zk-Proofs can enhance verifiable and privacy-preserving AI inference, assess their practicality, and determine the best way to integrate them.
By approaching it as an initial research stage, we can carefully evaluate the benefits and challenges without overextending our resources. Based on our findings, we'll decide whether to proceed with a full implementation in later phases or adjust our strategy accordingly. This approach helps us manage complexity and costs while remaining flexible to incorporate zk-Proofs effectively if they prove feasible within our project's scope.
I feel like even if the idea is in the right direction Arbitrum would benefit more from multiple project submissions instead of a single one under this on chain AI topic.
I feel like even if the idea is in the right direction Arbitrum would benefit more from multiple project submissions instead of a single one under this on chain AI topic.
Hey @0x_ultra , thanks for bringing this up! I really appreciate your perspective and completely agree that Arbitrum would benefit from a diverse range of projects exploring on-chain AI.
The idea behind our proposal is actually to enable exactly that. By building a foundational framework and providing the necessary tools, we're aiming to lower the barriers for many developers to create their own AI-powered applications on Arbitrum. Instead of focusing on a single model or project, we're working to create infrastructure that everyone can use, which we believe will stimulate more innovation and a variety of projects in the ecosystem.
I see our efforts as complementary to the existing grants program. By establishing this groundwork, we can enhance the effectiveness of bounties and grants by providing developers with the resources they need to build more sophisticated and efficient on-chain AI solutions.
I’m excited about the potential for collaboration here. Maybe we can integrate our framework with the grants program to encourage more submissions and make it easier for developers to participate. I'd love to hear any ideas you have on how we can maximize the benefits for the community and work together to drive innovation in this space.
Thanks again for your input! Let’s keep the conversation going.
It would be helpful if you elaborated on what those challenges were exactly. Were they specific technical limitations, such as gas costs, performance, or compatibility issues with Stylus? A deeper analysis of these problems could not only strengthen the justification for your proposal but also provide clearer direction for the project from the outset.
It would be helpful if you elaborated on what those challenges were exactly. Were they specific technical limitations, such as gas costs, performance, or compatibility issues with Stylus? A deeper analysis of these problems could not only strengthen the justification for your proposal but also provide clearer direction for the project from the outset.
How These Challenges Inform Our Proposal:
Understanding these challenges has been instrumental in shaping the objectives and methodology of our project:
developing a framework for deploying and interacting with AI models onchain using Arbitrum Stylus and Rust
Hello @jameskbh.
Thanks for the compliment and questions, below find the reponses
1. At the end of Phase 2, you mention the publishing of a feasibility report. What would happen if the results so far show that it is not feasible to continue?
Hello @jameskbh.
Thanks for the compliment and questions, below find the reponses
1. At the end of Phase 2, you mention the publishing of a feasibility report. What would happen if the results so far show that it is not feasible to continue?
If the feasibility report at the end of Phase 2 concludes that the project is not viable to continue, the unspent funds would be returned to the DAO or redirected to other community initiatives based on a transparent decision process. This ensures that the resources are used responsibly and remain aligned with the interests of the Arbitrum ecosystem.
2. Who will decide if it is feasible or not? Is there any external entity taking part in this?
The decision on feasibility will be based on the findings of the feasibility report, which will include clear metrics and benchmarks to evaluate the project's progress. The results will be shared transparently with the DAO for review, and the community will play a significant role in determining the next steps.
While no external entities are currently involved, we are open to engaging independent experts or advisors to provide an unbiased evaluation of the report if the DAO recommends it.
3. Could you break down the budget/cost to match the implementation steps?
Certainly! Here’s a breakdown aligned with the implementation phases:
4. Would you be open to receive the funds as a stream, instead of the full amount upfront?
Yes, we are open to receiving the funds as a stream rather than the full amount upfront. A phased funding approach aligns well with the project’s structure, as it allows the DAO to track progress and ensure that resources are being used effectively. The funds could be released incrementally at the start of each phase, contingent on successful completion and reporting of the previous phase. This approach provides transparency and accountability, which we fully support.
Have you checked out the Trailbrazer AI Grant Program? The Arbitrum Foundation just announced it.
Hello @0xDonPepe
Have you checked out the Trailbrazer AI Grant Program? The Arbitrum Foundation just announced it.
Hello @0xDonPepe
Yes, I've seen the Trailblazer AI Grant Program, and it's a fantastic initiative for supporting AI projects within the community. However, the program has a cap of $10,000 per project, which isn't sufficient for the scale of our proposal. Our project involves significant research and development to build onchain infrastructure for AI on Arbitrum. This includes developing a comprehensive framework, tools, and open-source resources that require a larger budget to execute effectively. That's why we're seeking funding through this proposal to ensure we can deliver meaningful results that benefit the entire ecosystem.
Specifically on this proposal, the use cases you’ve highlighted, particularly around decentralized AI decision-making and smart contract automation, are very interesting. These applications demonstrate the transformative potential of integrating AI directly with smart contracts and showcase Arbitrum’s ability to lead in this innovative space.
The project will release open-source tools and developer education materials to empower the broader Arbitrum community.
The emphasis on open-source tools and developer education demonstrates a strong commitment to community building. Have you considered creating beginner-friendly templates, example projects, or a flow to lower the entry barrier for developers unfamiliar with AI or Rust?
Hello, thanks for your great input on the proposal.
Absolutely! We totally get that not everyone is familiar with AI or Rust. We're planning to create beginner-friendly templates and example projects to help developers get started quickly. Our goal is to lower the entry barrier and make it easy for anyone to dive in, even if they're new to these technologies. We'll provide step-by-step guides and resources to support developers of all skill levels.
We appreciate your attention to these points to strengthen the proposal.
Thank you for catching that error in the timeline! We'll adjust the proposal to reflect this.
We'll ensure all dates align correctly with the voting schedule. Thank you again for your attention to detail. we appreciate your help in strengthening the proposal!
In the first phase, you mentioned testing Stylus’ scalability for AI models. If performance or compatibility bottlenecks are discovered, how will the project be adjusted?
In the third phase, you plan to optimize the framework and support more complex models within just two months. Isn’t that timeframe too short? Do you have a contingency plan to handle potential delays?
If we find bottlenecks in Phase 1:
If we run into performance or compatibility issues, we'll adapt our approach. This might mean optimizing our models, tweaking the code, or exploring alternative solutions to overcome the challenges. Our goal is to ensure the project remains valuable and feasible, so we're prepared to adjust as needed.
You're right; two months is ambitious for optimizing complex models. We have contingency plans in place. If we need more time to maintain quality, we'll adjust the schedule. Our priority is to deliver a robust framework, even if it means extending the timeline a bit. We also have buffer times included in our time frame.
Really appreciate your insights! We're committed to making this project a success.
Thank you for your thoughtful feedback and for seeing the potential benefits of the proposal for the DAO. I appreciate your observations.
Regarding your question about timelines and budget: If we find that we cannot meet the proposed timelines, we are committed to completing the project within the same budget. We will not request additional funding. Instead, we'll adjust our approach and allocate our resources efficiently to ensure we deliver the promised outcomes.
Our priority is to responsibly manage the resources provided and to maintain transparency with the DAO throughout the project's execution. If any delays or significant changes arise, we'll promptly communicate them to keep everyone informed and to discuss the best way forward.
I'm confident that with careful planning and open communication, we'll successfully execute the proposal.
you could add more specific metrics… such as the number of active developers or projects adopting your framework within a given timeframe
Great question! We definitely plan to measure success with specific metrics. Besides releasing the open-source tools and libraries, we'll be tracking:
Additionally, if community developers want to build upon this project, do you have any incentive plans, such as hosting hackathons or offering grant rewards?”
Additionally, if community developers want to build upon this project, do you have any incentive plans, such as hosting hackathons or offering grant rewards?”
Absolutely! We plan to actively encourage and support community developers who want to build on our project. Hosting hackathons is definitely on our agenda to foster innovation and collaboration. We're also looking into collaborating with grants teams in the ecosystem or offering rewards for standout projects that utilize our framework. Our aim is to create a vibrant ecosystem around on-chain AI, and empowering developers is a big part of that. We're excited to see the amazing things the community will create!
The direction of on-chain AI is indeed cutting-edge, but given the current high demand for DeFi and gaming on-chain applications, does your choice of on-chain AI models have specific use cases to support it? For instance, what scenarios could your decision tree model be practically applied to?
The direction of on-chain AI is indeed cutting-edge, but given the current high demand for DeFi and gaming on-chain applications, does your choice of on-chain AI models have specific use cases to support it? For instance, what scenarios could your decision tree model be practically applied to?
Great question! Absolutely, our on-chain AI models have specific use cases in both DeFi and gaming.
In DeFi, a decision tree model can be used for on-chain credit scoring. For example, it can analyze a user's transaction history, asset holdings, and interaction patterns to assess creditworthiness. This allows decentralized lending platforms to make smarter lending decisions without relying on off-chain data, enhancing trust and efficiency in lending protocols.
In gaming, decision trees can drive dynamic in-game events or NPC behaviors. For instance, in a blockchain-based game, the model could determine outcomes based on player choices, such as unlocking special quests or adapting enemy strategies. This adds a layer of complexity and personalization that enhances the gaming experience.
By deploying these models on-chain, we ensure transparency and trust in the decision-making process, which is crucial for decentralized applications.
The project will release open-source tools and developer education materials to empower the broader Arbitrum community.
The project will release open-source tools and developer education materials to empower the broader Arbitrum community.
This is key to success. But have you considered more proactive strategies to engage the community? Virtual hackathons, rewards for projects using your framework, or collaborations with prominent developers could be excellent ways to increase adoption and the project’s impact.
Yes, absolutely! We plan to engage in developer partnerships and host hackathons, especially after completing the first iteration of our initiative. Right now, our main focus is on bringing the framework to reality. Once it's established, we'll actively encourage developers to build applications leveraging the infrastructure we've created. Community engagement is entirely in our plan, and we're excited to foster innovation within the Arbitrum ecosystem.
Given the timeline and estimated budget, how do you plan to handle the complexity and cost this entails? Perhaps you could clarify whether this will be an initial implementation or just a research stage within the project. This would help to structure the phases.
Our plan is to initially focus on research and feasibility during the early phases of the project. This means we'll explore how zk-Proofs can enhance verifiable and privacy-preserving AI inference, assess their practicality, and determine the best way to integrate them.
By approaching it as an initial research stage, we can carefully evaluate the benefits and challenges without overextending our resources. Based on our findings, we'll decide whether to proceed with a full implementation in later phases or adjust our strategy accordingly. This approach helps us manage complexity and costs while remaining flexible to incorporate zk-Proofs effectively if they prove feasible within our project's scope.
I feel like even if the idea is in the right direction Arbitrum would benefit more from multiple project submissions instead of a single one under this on chain AI topic.
I feel like even if the idea is in the right direction Arbitrum would benefit more from multiple project submissions instead of a single one under this on chain AI topic.
Hey @0x_ultra , thanks for bringing this up! I really appreciate your perspective and completely agree that Arbitrum would benefit from a diverse range of projects exploring on-chain AI.
The idea behind our proposal is actually to enable exactly that. By building a foundational framework and providing the necessary tools, we're aiming to lower the barriers for many developers to create their own AI-powered applications on Arbitrum. Instead of focusing on a single model or project, we're working to create infrastructure that everyone can use, which we believe will stimulate more innovation and a variety of projects in the ecosystem.
I see our efforts as complementary to the existing grants program. By establishing this groundwork, we can enhance the effectiveness of bounties and grants by providing developers with the resources they need to build more sophisticated and efficient on-chain AI solutions.
I’m excited about the potential for collaboration here. Maybe we can integrate our framework with the grants program to encourage more submissions and make it easier for developers to participate. I'd love to hear any ideas you have on how we can maximize the benefits for the community and work together to drive innovation in this space.
Thanks again for your input! Let’s keep the conversation going.
It would be helpful if you elaborated on what those challenges were exactly. Were they specific technical limitations, such as gas costs, performance, or compatibility issues with Stylus? A deeper analysis of these problems could not only strengthen the justification for your proposal but also provide clearer direction for the project from the outset.
It would be helpful if you elaborated on what those challenges were exactly. Were they specific technical limitations, such as gas costs, performance, or compatibility issues with Stylus? A deeper analysis of these problems could not only strengthen the justification for your proposal but also provide clearer direction for the project from the outset.
How These Challenges Inform Our Proposal:
Understanding these challenges has been instrumental in shaping the objectives and methodology of our project:
developing a framework for deploying and interacting with AI models onchain using Arbitrum Stylus and Rust
Hello @jameskbh.
Thanks for the compliment and questions, below find the reponses
1. At the end of Phase 2, you mention the publishing of a feasibility report. What would happen if the results so far show that it is not feasible to continue?
Hello @jameskbh.
Thanks for the compliment and questions, below find the reponses
1. At the end of Phase 2, you mention the publishing of a feasibility report. What would happen if the results so far show that it is not feasible to continue?
If the feasibility report at the end of Phase 2 concludes that the project is not viable to continue, the unspent funds would be returned to the DAO or redirected to other community initiatives based on a transparent decision process. This ensures that the resources are used responsibly and remain aligned with the interests of the Arbitrum ecosystem.
2. Who will decide if it is feasible or not? Is there any external entity taking part in this?
The decision on feasibility will be based on the findings of the feasibility report, which will include clear metrics and benchmarks to evaluate the project's progress. The results will be shared transparently with the DAO for review, and the community will play a significant role in determining the next steps.
While no external entities are currently involved, we are open to engaging independent experts or advisors to provide an unbiased evaluation of the report if the DAO recommends it.
3. Could you break down the budget/cost to match the implementation steps?
Certainly! Here’s a breakdown aligned with the implementation phases:
4. Would you be open to receive the funds as a stream, instead of the full amount upfront?
Yes, we are open to receiving the funds as a stream rather than the full amount upfront. A phased funding approach aligns well with the project’s structure, as it allows the DAO to track progress and ensure that resources are being used effectively. The funds could be released incrementally at the start of each phase, contingent on successful completion and reporting of the previous phase. This approach provides transparency and accountability, which we fully support.
Have you checked out the Trailbrazer AI Grant Program? The Arbitrum Foundation just announced it.
Hello @0xDonPepe
Have you checked out the Trailbrazer AI Grant Program? The Arbitrum Foundation just announced it.
Hello @0xDonPepe
Yes, I've seen the Trailblazer AI Grant Program, and it's a fantastic initiative for supporting AI projects within the community. However, the program has a cap of $10,000 per project, which isn't sufficient for the scale of our proposal. Our project involves significant research and development to build onchain infrastructure for AI on Arbitrum. This includes developing a comprehensive framework, tools, and open-source resources that require a larger budget to execute effectively. That's why we're seeking funding through this proposal to ensure we can deliver meaningful results that benefit the entire ecosystem.
Specifically on this proposal, the use cases you’ve highlighted, particularly around decentralized AI decision-making and smart contract automation, are very interesting. These applications demonstrate the transformative potential of integrating AI directly with smart contracts and showcase Arbitrum’s ability to lead in this innovative space.
developing a framework for deploying and interacting with AI models onchain using Arbitrum Stylus and Rust
? Including an analysis of their work or even highlighting lessons learned could enrich your project and help avoid redundancies…
Yes, I'm aware of "The Real Open AI" project from the Bucharest hackathon, and I think it's fantastic that they're exploring similar use cases with Arbitrum Stylus. I've taken the time to look into their approach to understand how it compares to what we're proposing. If our infra was live by then, they could have used our platform to build "The Real Open AI".
Their Approach:
Our Proposal and Key Differences:
While "The Real Open AI" project and our proposal share the common goal of bringing AI models onchain using Arbitrum Stylus, our approaches differ in scale and methodology. Their project demonstrated the feasibility and highlighted some challenges, primarily focusing on a specific use case with Solidity.
Our proposal builds on these insights but aims to create a more robust and scalable solution by developing a comprehensive framework using Rust and Stylus. We believe this will address the limitations they encountered and open up broader possibilities for AI applications on Arbitrum.
Specifically on this proposal, the use cases you’ve highlighted, particularly around decentralized AI decision-making and smart contract automation, are very interesting. These applications demonstrate the transformative potential of integrating AI directly with smart contracts and showcase Arbitrum’s ability to lead in this innovative space.
Because of these, we are generally supportive of the proposal. It balances bold ambition with a practical plan. We appreciate and want to highlight the importance of redirecting funds to other initiatives if the project is deemed unfeasible in Phase 2. It ensures we encourage big ideas, while making sure DAO resources are used effectively.
Wow @karpatkey, thanks so much for your amazing feedback! I'm super excited that you're as hyped about Stylus as I am. Bringing more engineers and developers into the Arbitrum ecosystem is such a game-changer, and it's awesome to see others sharing that vision.
We're just scratching the surface. Can't wait to see where this innovation takes us and how Arbitrum can lead the charge.
Really appreciate your support on the proposal. Balancing ambitious dreams with practical steps is key, We're all about making bold moves while ensuring the DAO's resources are used wisely.
Thanks again for the encouragement! Let's push the boundaries together and make some magic happen!
Product to be Audited: The on-chain AI framework/infrastructure, including smart contracts, Rust libraries, and any deployed code.
Personnel:
Total Cost Calculation:
Generally, I am supportive of it. But, I’d like to ask a clarification on funding. Do you expect to seek funding from other places as well or would this be funded by Arbitrum DAO only? For example, the Arbitrum Foundation has recently launched the Trailblazer grant program, specifically focused on powering AI innovation on Arbitrum. This project might be a good fit for it.
Generally, I am supportive of it. But, I’d like to ask a clarification on funding. Do you expect to seek funding from other places as well or would this be funded by Arbitrum DAO only? For example, the Arbitrum Foundation has recently launched the Trailblazer grant program, specifically focused on powering AI innovation on Arbitrum. This project might be a good fit for it.
Hi @alicecorsini
Thank you for your support and for recognizing Stylus as a key competitive advantage for Arbitrum! We're excited to contribute to leveraging its potential within the ecosystem.
Regarding your question about funding, we're currently seeking support solely from the Arbitrum DAO for this project. The scope of our proposal involves significant research and development to build comprehensive onchain AI infrastructure using Stylus and Rust. This includes developing open-source tools, frameworks, and documentation that will benefit the entire Arbitrum community.
We have considered the Trailblazer AI Grant Program, and we think it's a fantastic initiative. However, the program has a funding cap of $10,000 per project, which isn't sufficient for the scale and ambitions of our proposal. Our project requires a larger budget to cover the extensive development efforts and resources needed to achieve our goals.
By seeking funding from the DAO, we aim to ensure that the project's outcomes align closely with the community's interests and that we can deliver meaningful contributions to the ecosystem. We believe this approach allows us to make a more significant impact and fully realize the potential of integrating AI with Stylus on Arbitrum.
Thank you again for your support!
Arbitrum does not have this now, why do we need to do this here?
@cp0x
Even though Arbitrum doesn't currently have built-in support for zero-knowledge proofs (zk-proofs), integrating them into our project is important for several reasons:
In Simple Terms:
Hello @NathanVDH,
Thank you for sharing your thoughts. I appreciate your perspective and the opportunity to clarify our intentions.
Hello @NathanVDH,
Thank you for sharing your thoughts. I appreciate your perspective and the opportunity to clarify our intentions.
Our primary goal with this proposal is to contribute to the Arbitrum ecosystem by building open-source infrastructure that benefits the entire community. By developing a framework for deploying AI models onchain using Stylus and Rust, we're aiming to create tools and resources that any developer can use to innovate and expand the capabilities of decentralized applications on Arbitrum.
This project isn't about establishing a proprietary business or generating profits—it's about fostering innovation within the community. The funds requested are allocated toward development costs, infrastructure, and creating open-source tools that will be freely available to everyone in the ecosystem.
Seeking venture funding often comes with expectations of proprietary ownership and a focus on financial returns, which might limit accessibility and openness. By collaborating with the DAO, we ensure that the project's outcomes remain community-driven and aligned with the collective interests of Arbitrum users and developers.
I understand your concerns, and I hope this explanation provides clarity on why we're seeking support from the DAO rather than venture capital. I'm open to further discussion if you have additional questions or suggestions. Your feedback is valuable, and I appreciate you taking the time to engage with the proposal.
What does this mean? Scalability in what sense, I did not quite understand what the result should be.
Hello @cp0x
What does this mean? Scalability in what sense, I did not quite understand what the result should be.
Hello @cp0x
Great question! When we refer to the "scalability of Stylus for AI models," we're talking about the ability of the Arbitrum Stylus platform to efficiently handle the deployment and execution of AI models on the blockchain, especially as the complexity of the models or the number of users increases.
Here's what that means in more detail:
Hello @paulofonseca.
Yes, I did follow the Stylus hackathon and was impressed by "The Real Open AI" project. Their work showcased the exciting possibilities of bringing AI models onchain using Arbitrum Stylus. Their approach to democratizing AI and involving the community through NFTs is inspiring and highlights the innovative spirit within the Arbitrum ecosystem.
Hello @paulofonseca.
Yes, I did follow the Stylus hackathon and was impressed by "The Real Open AI" project. Their work showcased the exciting possibilities of bringing AI models onchain using Arbitrum Stylus. Their approach to democratizing AI and involving the community through NFTs is inspiring and highlights the innovative spirit within the Arbitrum ecosystem.
My proposal aligns with this vision but takes a different approach by focusing on building the foundational infrastructure for onchain AI development. Instead of developing a single application or model, we aim to create a comprehensive framework, including tools, libraries, and documentation, that will make it easier for anyone to build and deploy AI models on Stylus using Rust.
By concentrating on the underlying infrastructure, we hope to empower developers to explore a wide range of AI applications onchain, from simple models to more complex systems. This will not only broaden the use cases for Arbitrum Stylus but also foster a community of innovators who can contribute to the growth and diversification of the ecosystem.
In essence, while "The Real Open AI" project demonstrated the potential of onchain AI through a specific application, our proposal seeks to expand that potential by providing the resources and infrastructure necessary for widespread adoption and development of onchain AI models on Stylus.
Optimize the framework for larger datasets and more complex models
developing a framework for deploying and interacting with AI models onchain using Arbitrum Stylus and Rust
? Including an analysis of their work or even highlighting lessons learned could enrich your project and help avoid redundancies…
Yes, I'm aware of "The Real Open AI" project from the Bucharest hackathon, and I think it's fantastic that they're exploring similar use cases with Arbitrum Stylus. I've taken the time to look into their approach to understand how it compares to what we're proposing. If our infra was live by then, they could have used our platform to build "The Real Open AI".
Their Approach:
Our Proposal and Key Differences:
While "The Real Open AI" project and our proposal share the common goal of bringing AI models onchain using Arbitrum Stylus, our approaches differ in scale and methodology. Their project demonstrated the feasibility and highlighted some challenges, primarily focusing on a specific use case with Solidity.
Our proposal builds on these insights but aims to create a more robust and scalable solution by developing a comprehensive framework using Rust and Stylus. We believe this will address the limitations they encountered and open up broader possibilities for AI applications on Arbitrum.
Specifically on this proposal, the use cases you’ve highlighted, particularly around decentralized AI decision-making and smart contract automation, are very interesting. These applications demonstrate the transformative potential of integrating AI directly with smart contracts and showcase Arbitrum’s ability to lead in this innovative space.
Because of these, we are generally supportive of the proposal. It balances bold ambition with a practical plan. We appreciate and want to highlight the importance of redirecting funds to other initiatives if the project is deemed unfeasible in Phase 2. It ensures we encourage big ideas, while making sure DAO resources are used effectively.
Wow @karpatkey, thanks so much for your amazing feedback! I'm super excited that you're as hyped about Stylus as I am. Bringing more engineers and developers into the Arbitrum ecosystem is such a game-changer, and it's awesome to see others sharing that vision.
We're just scratching the surface. Can't wait to see where this innovation takes us and how Arbitrum can lead the charge.
Really appreciate your support on the proposal. Balancing ambitious dreams with practical steps is key, We're all about making bold moves while ensuring the DAO's resources are used wisely.
Thanks again for the encouragement! Let's push the boundaries together and make some magic happen!
Product to be Audited: The on-chain AI framework/infrastructure, including smart contracts, Rust libraries, and any deployed code.
Personnel:
Total Cost Calculation:
Generally, I am supportive of it. But, I’d like to ask a clarification on funding. Do you expect to seek funding from other places as well or would this be funded by Arbitrum DAO only? For example, the Arbitrum Foundation has recently launched the Trailblazer grant program, specifically focused on powering AI innovation on Arbitrum. This project might be a good fit for it.
Generally, I am supportive of it. But, I’d like to ask a clarification on funding. Do you expect to seek funding from other places as well or would this be funded by Arbitrum DAO only? For example, the Arbitrum Foundation has recently launched the Trailblazer grant program, specifically focused on powering AI innovation on Arbitrum. This project might be a good fit for it.
Hi @alicecorsini
Thank you for your support and for recognizing Stylus as a key competitive advantage for Arbitrum! We're excited to contribute to leveraging its potential within the ecosystem.
Regarding your question about funding, we're currently seeking support solely from the Arbitrum DAO for this project. The scope of our proposal involves significant research and development to build comprehensive onchain AI infrastructure using Stylus and Rust. This includes developing open-source tools, frameworks, and documentation that will benefit the entire Arbitrum community.
We have considered the Trailblazer AI Grant Program, and we think it's a fantastic initiative. However, the program has a funding cap of $10,000 per project, which isn't sufficient for the scale and ambitions of our proposal. Our project requires a larger budget to cover the extensive development efforts and resources needed to achieve our goals.
By seeking funding from the DAO, we aim to ensure that the project's outcomes align closely with the community's interests and that we can deliver meaningful contributions to the ecosystem. We believe this approach allows us to make a more significant impact and fully realize the potential of integrating AI with Stylus on Arbitrum.
Thank you again for your support!
Arbitrum does not have this now, why do we need to do this here?
@cp0x
Even though Arbitrum doesn't currently have built-in support for zero-knowledge proofs (zk-proofs), integrating them into our project is important for several reasons:
In Simple Terms:
Hello @NathanVDH,
Thank you for sharing your thoughts. I appreciate your perspective and the opportunity to clarify our intentions.
Hello @NathanVDH,
Thank you for sharing your thoughts. I appreciate your perspective and the opportunity to clarify our intentions.
Our primary goal with this proposal is to contribute to the Arbitrum ecosystem by building open-source infrastructure that benefits the entire community. By developing a framework for deploying AI models onchain using Stylus and Rust, we're aiming to create tools and resources that any developer can use to innovate and expand the capabilities of decentralized applications on Arbitrum.
This project isn't about establishing a proprietary business or generating profits—it's about fostering innovation within the community. The funds requested are allocated toward development costs, infrastructure, and creating open-source tools that will be freely available to everyone in the ecosystem.
Seeking venture funding often comes with expectations of proprietary ownership and a focus on financial returns, which might limit accessibility and openness. By collaborating with the DAO, we ensure that the project's outcomes remain community-driven and aligned with the collective interests of Arbitrum users and developers.
I understand your concerns, and I hope this explanation provides clarity on why we're seeking support from the DAO rather than venture capital. I'm open to further discussion if you have additional questions or suggestions. Your feedback is valuable, and I appreciate you taking the time to engage with the proposal.
What does this mean? Scalability in what sense, I did not quite understand what the result should be.
Hello @cp0x
What does this mean? Scalability in what sense, I did not quite understand what the result should be.
Hello @cp0x
Great question! When we refer to the "scalability of Stylus for AI models," we're talking about the ability of the Arbitrum Stylus platform to efficiently handle the deployment and execution of AI models on the blockchain, especially as the complexity of the models or the number of users increases.
Here's what that means in more detail:
Hello @paulofonseca.
Yes, I did follow the Stylus hackathon and was impressed by "The Real Open AI" project. Their work showcased the exciting possibilities of bringing AI models onchain using Arbitrum Stylus. Their approach to democratizing AI and involving the community through NFTs is inspiring and highlights the innovative spirit within the Arbitrum ecosystem.
Hello @paulofonseca.
Yes, I did follow the Stylus hackathon and was impressed by "The Real Open AI" project. Their work showcased the exciting possibilities of bringing AI models onchain using Arbitrum Stylus. Their approach to democratizing AI and involving the community through NFTs is inspiring and highlights the innovative spirit within the Arbitrum ecosystem.
My proposal aligns with this vision but takes a different approach by focusing on building the foundational infrastructure for onchain AI development. Instead of developing a single application or model, we aim to create a comprehensive framework, including tools, libraries, and documentation, that will make it easier for anyone to build and deploy AI models on Stylus using Rust.
By concentrating on the underlying infrastructure, we hope to empower developers to explore a wide range of AI applications onchain, from simple models to more complex systems. This will not only broaden the use cases for Arbitrum Stylus but also foster a community of innovators who can contribute to the growth and diversification of the ecosystem.
In essence, while "The Real Open AI" project demonstrated the potential of onchain AI through a specific application, our proposal seeks to expand that potential by providing the resources and infrastructure necessary for widespread adoption and development of onchain AI models on Stylus.
Optimize the framework for larger datasets and more complex models
Optimize the framework for larger datasets and more complex models
That is, our task is to create a framework for creating AI? I just did not find this in the text earlier.
Yes, you're correct! One of the primary goals of our proposal is to create a framework that enables developers to deploy and interact with AI models onchain using Arbitrum Stylus and Rust. Our task goes beyond implementing a single AI model; we're building the foundational infrastructure—including tools, libraries, and documentation—that will make it easier for anyone to create and optimize AI models for onchain deployment.
again @cp0x
Great question! When we mention "identifying the most suitable lightweight AI models for deployment," we're focusing on selecting AI models that are efficient, require minimal computational resources, and can operate effectively within the constraints of a blockchain environment like Arbitrum Stylus. Here's a detailed explanation of the options and how we can use AI models in our case.
1. Linear Models
2. Decision Trees
3. Naive Bayes Classifier
4. Rule-Based Systems
5. Simple Neural Networks
Our goal is to develop a framework that allows developers to deploy and interact with AI models on Arbitrum Stylus. Here's how we can use these AI models:
1. Onchain Inference
2. Automated Decision-Making in Smart Contracts
3. Enhancing NFTs with AI
4. Verifiable Computations
1. Decentralized Finance (DeFi)
2. Supply Chain Management
3. Gaming and NFTs
4. Identity and Reputation Systems
Optimize the framework for larger datasets and more complex models
That is, our task is to create a framework for creating AI? I just did not find this in the text earlier.
Yes, you're correct! One of the primary goals of our proposal is to create a framework that enables developers to deploy and interact with AI models onchain using Arbitrum Stylus and Rust. Our task goes beyond implementing a single AI model; we're building the foundational infrastructure—including tools, libraries, and documentation—that will make it easier for anyone to create and optimize AI models for onchain deployment.
again @cp0x
Great question! When we mention "identifying the most suitable lightweight AI models for deployment," we're focusing on selecting AI models that are efficient, require minimal computational resources, and can operate effectively within the constraints of a blockchain environment like Arbitrum Stylus. Here's a detailed explanation of the options and how we can use AI models in our case.
1. Linear Models
2. Decision Trees
3. Naive Bayes Classifier
4. Rule-Based Systems
5. Simple Neural Networks
Our goal is to develop a framework that allows developers to deploy and interact with AI models on Arbitrum Stylus. Here's how we can use these AI models:
1. Onchain Inference
2. Automated Decision-Making in Smart Contracts
3. Enhancing NFTs with AI
4. Verifiable Computations
1. Decentralized Finance (DeFi)
2. Supply Chain Management
3. Gaming and NFTs
4. Identity and Reputation Systems
I'm directionally in favour for this proposal but as others have mentioned, there are multiple assurances that are lacking. We need some mechanism to build trust in the team, which could be having the team complete some initial work and then ask for further funds, having an entity step-up to do oversight (the Foundation maybe but not sure they're setup for this), or otherwise some tight milestone management (with the downside of costing A LOT of delegate time for small things and the delegates not necessarily having the expertise).
This is an example of something we should have a Catalyst for, or well, the upcoming OpCo that could do some oversight... Tricky right now....
I'm directionally in favour for this proposal but as others have mentioned, there are multiple assurances that are lacking. We need some mechanism to build trust in the team, which could be having the team complete some initial work and then ask for further funds, having an entity step-up to do oversight (the Foundation maybe but not sure they're setup for this), or otherwise some tight milestone management (with the downside of costing A LOT of delegate time for small things and the delegates not necessarily having the expertise).
This is an example of something we should have a Catalyst for, or well, the upcoming OpCo that could do some oversight... Tricky right now....
I'm tempted to propose a temporary council, elected by the DAO, as a complicated but perhaps viable solution to not ignore the need for an stylus-based AI framework.
Or if this proposal is turned into an RFP, that works too. SO you can design the RFP with delegate feedback even if you don't get to do the dev work directly.
Thank you for providing such detailed responses to the questions raised so far. We look forward to seeing whether this proposal can pass through the DAO and the necessary evaluations. I personally think, and suggest, that you consider applying for funding in batches and executing in phases. This approach allows the community to monitor project progress in real-time while ensuring transparency and efficient use of funds.
Additionally, you could introduce internal audits first. Internal audits can identify and resolve fundamental issues early on, thereby reducing the workload and complexity of external audits. This not only helps save costs but also improves overall audit efficiency.
Thank you @0xredacted for this interesting proposal. While we like the idea of an open-source framework for projects to utilize in building AI agents. We have a few questions.
Can you provide your Github with past completed work for review? We agree with @KlausBrave that there isn’t much information provided to give us confidence that you are the right person/team to fund for this.
Thank you @0xredacted for this interesting proposal. While we like the idea of an open-source framework for projects to utilize in building AI agents. We have a few questions.
Can you provide your Github with past completed work for review? We agree with @KlausBrave that there isn’t much information provided to give us confidence that you are the right person/team to fund for this.
We share @Ignas’s thoughts. What are the potential security implications of enabling this tooling for development on Arbitrum?
However, I’m a bit concerned about security. With AI running on the blockchain, are there any security risks we should be worried about?
We would be supportive of disbursement in tranches and we see that you’re acceptable to those terms as well. For this proposal to go through, you’ll need:
i. to prove that you can carry out the project as planned ii. update the proposal to take into account disbursement in tranches iii. provide insights into the potential downsides / risks (possibly can be covered in the feasibility)
Thank you for providing very detailed replies to the questions that have been asked so far and we look forward to seeing if this proposal can pass the DAO and necessary evaluations. Good luck!
Here’s the translation，After reviewing the recent updates, I have a few questions:
Is there anyway you can use that $10,000 funding pool to complete Phase 1? I think that is a path that will see more delegate support. If you get vetted by the AF, and have some proof of concept to come to the DAO with a request for funds.
Hey @0xredacted , thank you for your reply! While I understand your point of view, I still believe that attracting more applications is more valuable than focusing on specific AI groundwork. What makes one's groundwork better than another? With an open application we could have multiple "groundwork" submissions exploring different approaches and once everything is submitted one can decide whats the best direction, and at the same time if some find useful what others submitted they can elaborate and innovate on the rest. I'm a big fan of letting the market decide what's best and maximising options. Moreover, another benefit of open calls is that they bring more eyes to Arbitrum's development and ecosystem, which is always a good thing. That said, I really like your idea but maybe we should consider a balanced approach that combines both strategies.
I think this is a promising proposal, and Arbitrum can expand their blockchain use cases with verifiable AI. However, I’m a bit concerned about security. With AI running on the blockchain, are there any security risks we should be worried about? Is there any mechanism in place to prevent these AI models from being exploited or misused by third parties? Also, I'm not sure what long-term benefits Arbitrum will gain from this.
The proposal is very forward-thinking, leveraging Stylus and Rust to enhance Arbitrum’s technical influence. However, I find the connection between the budget details and the expected outcomes a bit unclear. For instance, could the outcomes include some quantifiable metrics to provide a clearer picture of success?
I truly appreciate the initiative to build infrastructure for onboarding AI models on Arbitrum. However, I believe the real measure of success will be attracting developers to build and deploy AI models on this infrastructure. Achieving this would require robust marketing efforts to raise awareness and inspire developers to choose Arbitrum over other chains.
How do you propose we approach this? Additionally, how does this fit into the competitive landscape, especially considering that other L2s (example Mode Network) are significantly shifting their narrative toward AI agents?
Hi @0xredacted, creating useful infra for others wishing to build AI with stylus is a worthwhile pursuit. I agree with your counter-responses that applying for the 10k grants for your endeavour's shape and size is not appropriate.
I'm directionally in favour for this proposal but as others have mentioned, there are multiple assurances that are lacking. We need some mechanism to build trust in the team, which could be having the team complete some initial work and then ask for further funds, having an entity step-up to do oversight (the Foundation maybe but not sure they're setup for this), or otherwise some tight milestone management (with the downside of costing A LOT of delegate time for small things and the delegates not necessarily having the expertise).
This is an example of something we should have a Catalyst for, or well, the upcoming OpCo that could do some oversight... Tricky right now....
I'm directionally in favour for this proposal but as others have mentioned, there are multiple assurances that are lacking. We need some mechanism to build trust in the team, which could be having the team complete some initial work and then ask for further funds, having an entity step-up to do oversight (the Foundation maybe but not sure they're setup for this), or otherwise some tight milestone management (with the downside of costing A LOT of delegate time for small things and the delegates not necessarily having the expertise).
This is an example of something we should have a Catalyst for, or well, the upcoming OpCo that could do some oversight... Tricky right now....
I'm tempted to propose a temporary council, elected by the DAO, as a complicated but perhaps viable solution to not ignore the need for an stylus-based AI framework.
Or if this proposal is turned into an RFP, that works too. SO you can design the RFP with delegate feedback even if you don't get to do the dev work directly.
Thank you for providing such detailed responses to the questions raised so far. We look forward to seeing whether this proposal can pass through the DAO and the necessary evaluations. I personally think, and suggest, that you consider applying for funding in batches and executing in phases. This approach allows the community to monitor project progress in real-time while ensuring transparency and efficient use of funds.
Additionally, you could introduce internal audits first. Internal audits can identify and resolve fundamental issues early on, thereby reducing the workload and complexity of external audits. This not only helps save costs but also improves overall audit efficiency.
Thank you @0xredacted for this interesting proposal. While we like the idea of an open-source framework for projects to utilize in building AI agents. We have a few questions.
Can you provide your Github with past completed work for review? We agree with @KlausBrave that there isn’t much information provided to give us confidence that you are the right person/team to fund for this.
Thank you @0xredacted for this interesting proposal. While we like the idea of an open-source framework for projects to utilize in building AI agents. We have a few questions.
Can you provide your Github with past completed work for review? We agree with @KlausBrave that there isn’t much information provided to give us confidence that you are the right person/team to fund for this.
We share @Ignas’s thoughts. What are the potential security implications of enabling this tooling for development on Arbitrum?
However, I’m a bit concerned about security. With AI running on the blockchain, are there any security risks we should be worried about?
We would be supportive of disbursement in tranches and we see that you’re acceptable to those terms as well. For this proposal to go through, you’ll need:
i. to prove that you can carry out the project as planned ii. update the proposal to take into account disbursement in tranches iii. provide insights into the potential downsides / risks (possibly can be covered in the feasibility)
Thank you for providing very detailed replies to the questions that have been asked so far and we look forward to seeing if this proposal can pass the DAO and necessary evaluations. Good luck!
Here’s the translation，After reviewing the recent updates, I have a few questions:
Is there anyway you can use that $10,000 funding pool to complete Phase 1? I think that is a path that will see more delegate support. If you get vetted by the AF, and have some proof of concept to come to the DAO with a request for funds.
Hey @0xredacted , thank you for your reply! While I understand your point of view, I still believe that attracting more applications is more valuable than focusing on specific AI groundwork. What makes one's groundwork better than another? With an open application we could have multiple "groundwork" submissions exploring different approaches and once everything is submitted one can decide whats the best direction, and at the same time if some find useful what others submitted they can elaborate and innovate on the rest. I'm a big fan of letting the market decide what's best and maximising options. Moreover, another benefit of open calls is that they bring more eyes to Arbitrum's development and ecosystem, which is always a good thing. That said, I really like your idea but maybe we should consider a balanced approach that combines both strategies.
I think this is a promising proposal, and Arbitrum can expand their blockchain use cases with verifiable AI. However, I’m a bit concerned about security. With AI running on the blockchain, are there any security risks we should be worried about? Is there any mechanism in place to prevent these AI models from being exploited or misused by third parties? Also, I'm not sure what long-term benefits Arbitrum will gain from this.
The proposal is very forward-thinking, leveraging Stylus and Rust to enhance Arbitrum’s technical influence. However, I find the connection between the budget details and the expected outcomes a bit unclear. For instance, could the outcomes include some quantifiable metrics to provide a clearer picture of success?
I truly appreciate the initiative to build infrastructure for onboarding AI models on Arbitrum. However, I believe the real measure of success will be attracting developers to build and deploy AI models on this infrastructure. Achieving this would require robust marketing efforts to raise awareness and inspire developers to choose Arbitrum over other chains.
How do you propose we approach this? Additionally, how does this fit into the competitive landscape, especially considering that other L2s (example Mode Network) are significantly shifting their narrative toward AI agents?
Hi @0xredacted, creating useful infra for others wishing to build AI with stylus is a worthwhile pursuit. I agree with your counter-responses that applying for the 10k grants for your endeavour's shape and size is not appropriate.
Here’s the translation，After reviewing the recent updates, I have a few questions:
Suggestions:
• Increase the contingency fund: Consider raising it from $5,000 to $10,000, making it 5% of the total budget, to address potential unforeseen technical challenges or delays.
Suggestions:
• Establish a long-term incentive fund (e.g., $20,000) to support community developers in building open-source tools or extension modules. Additionally, consider hosting activities like regular online/offline workshops or hackathons (in collaboration with EthGlobal) to help developers onboard the framework more efficiently.
• Launch collaborative projects with existing DeFi or NFT initiatives to showcase practical use cases of the AI framework, such as on-chain prediction markets or dynamic NFTs.
Hi @0xredacted, creating useful infra for others wishing to build AI with stylus is a worthwhile pursuit. I agree with your counter-responses that applying for the 10k grants for your endeavour's shape and size is not appropriate.
@AnaTech.eth @aj_eth consider activating Arbitrum to sponsor the above AI Hackathon.
Thank you for the proposal. We find it innovative and believe that, if communicated effectively, it could bring benefits to the DAO. However, we have some observations:
Timelines and budget: If you cannot meet the proposed timelines, will you request additional funding, or will you continue working with the same budget until completion? This should be clarified to ensure that approved proposals are successfully executed.
Amounts in ARB: The amounts are listed in dollars, but it should be specified that they will be paid in ARB, as is standard for all proposals.
Publication of results: Will the results be published on the forum? What is the estimated timeframe for publication upon completion? We suggest monthly updates to keep the community informed and a final evaluation a few months after completion to assess success.
Timeline error: There seems to be an error in the timeline; voting periods start on Thursdays each week.
Thank you for the proposal. We find it innovative and believe that, if communicated effectively, it could bring benefits to the DAO. However, we have some observations:
Timelines and budget: If you cannot meet the proposed timelines, will you request additional funding, or will you continue working with the same budget until completion? This should be clarified to ensure that approved proposals are successfully executed.
Amounts in ARB: The amounts are listed in dollars, but it should be specified that they will be paid in ARB, as is standard for all proposals.
Publication of results: Will the results be published on the forum? What is the estimated timeframe for publication upon completion? We suggest monthly updates to keep the community informed and a final evaluation a few months after completion to assess success.
Timeline error: There seems to be an error in the timeline; voting periods start on Thursdays each week.
We appreciate your attention to these points to strengthen the proposal.
The following reflects the views of the Lampros DAO (formerly ‘Lampros Labs DAO’) governance team, composed of Chain_L (@Blueweb), @Euphoria, and Hirangi Pandya (@Nyx), based on our combined research, analysis, and ideation.
Thank you for putting forward this detailed proposal.
The integration of AI models on-chain using Stylus is a great approach.
The following reflects the views of the Lampros DAO (formerly ‘Lampros Labs DAO’) governance team, composed of Chain_L (@Blueweb), @Euphoria, and Hirangi Pandya (@Nyx), based on our combined research, analysis, and ideation.
Thank you for putting forward this detailed proposal.
The integration of AI models on-chain using Stylus is a great approach.
The project will release open-source tools and developer education materials to empower the broader Arbitrum community.
The emphasis on open-source tools and developer education demonstrates a strong commitment to community building. Have you considered creating beginner-friendly templates, example projects, or a flow to lower the entry barrier for developers unfamiliar with AI or Rust?
Also, would you consider offering developer bounties or hosting competitions to encourage early adoption? We believe incentivizing innovative use cases could rapidly grow the pool of Stylus-based projects.
Conduct a detailed study on the scalability of Stylus for AI models.
We’re interested in learning more about the approach planned for this study. Could you share the specific methodologies or key factors you plan to analyze during this phase? Understanding these details would help clarify how this phase will inform the project’s next steps.
“Your implementation plan is divided into four phases, which looks clear, but I have two questions: 1. In the first phase, you mentioned testing Stylus’ scalability for AI models. If performance or compatibility bottlenecks are discovered, how will the project be adjusted? 2. In the third phase, you plan to optimize the framework and support more complex models within just two months. Isn’t that timeframe too short? Do you have a contingency plan to handle potential delays?
The direction of on-chain AI is indeed cutting-edge, but given the current high demand for DeFi and gaming on-chain applications, does your choice of on-chain AI models have specific use cases to support it? For instance, what scenarios could your decision tree model be practically applied to?
“Your implementation plan is divided into four phases, which looks clear, but I have two questions: 1. In the first phase, you mentioned testing Stylus’ scalability for AI models. If performance or compatibility bottlenecks are discovered, how will the project be adjusted? 2. In the third phase, you plan to optimize the framework and support more complex models within just two months. Isn’t that timeframe too short? Do you have a contingency plan to handle potential delays?
The direction of on-chain AI is indeed cutting-edge, but given the current high demand for DeFi and gaming on-chain applications, does your choice of on-chain AI models have specific use cases to support it? For instance, what scenarios could your decision tree model be practically applied to?
Additionally, if community developers want to build upon this project, do you have any incentive plans, such as hosting hackathons or offering grant rewards?”
Additionally, is there room for budget optimization? For example, the costs for cloud computing and data collection could potentially be reduced by seeking community collaboration, such as partnering with existing Arbitrum projects to share resources and expenses.
This seems like a potentially worthwhile business, at least that's how you're selling it to the DAO. I think you should look at venture funding for something like this rather than asking the DAO. I'll be voting no on this proposal.
Hey there, I agree that Arbitrum with Stylus is in a unique position to enable AI interactions in a much more complete way with respect to other EVMs but I’m not sure how much it makes sense to spend directly for someone to build what you described. Since Arbitrum already has a grants https://x.com/arbitrum/status/1861792767548043430?s=46 for ai development would it just make more sense to add this “on chain model” as an extra bounty to the program?
I feel like even if the idea is in the right direction Arbitrum would benefit more from multiple project submissions instead of a single one under this on chain AI topic.
Hi! the proposal is not bad at all; it is well-intentioned, but I have some questions:
Regarding the initial challenges you mentioned:
Inspired by this, I conducted an experiment deploying a decision tree model using Stylus and Rust, which proved functional but highlighted challenges.
Hi! the proposal is not bad at all; it is well-intentioned, but I have some questions:
Regarding the initial challenges you mentioned:
Inspired by this, I conducted an experiment deploying a decision tree model using Stylus and Rust, which proved functional but highlighted challenges.
It would be helpful if you elaborated on what those challenges were exactly. Were they specific technical limitations, such as gas costs, performance, or compatibility issues with Stylus? A deeper analysis of these problems could not only strengthen the justification for your proposal but also provide clearer direction for the project from the outset.
I understand you are aware of the recent hackathon in Bucharest, but considering that the winning team, "The Real Open AI," attempted to address a similar use case, have you already explored how their approach compares to your proposal? For instance, what tools or models did they use, and what are the key differences in your implementation with:
developing a framework for deploying and interacting with AI models onchain using Arbitrum Stylus and Rust
I am also interested in your approach to zk-Proofs, where you state:
Given the timeline and estimated budget, how do you plan to handle the complexity and cost this entails? Perhaps you could clarify whether this will be an initial implementation or just a research stage within the project. This would help to structure the phases.
Regarding the community, you mention:
The project will release open-source tools and developer education materials to empower the broader Arbitrum community.
This is key to success. But have you considered more proactive strategies to engage the community? Virtual hackathons, rewards for projects using your framework, or collaborations with prominent developers could be excellent ways to increase adoption and the project's impact.
Finally, how do you plan to measure success in the implementation and adoption of these tools by the community? While you mention milestones like the
you could add more specific metrics… such as the number of active developers or projects adopting your framework within a given timeframe
Hello! Thanks for your proposal!
While it seems a nice idea, I have a few questions about the execution:
Hello! Thanks for your proposal!
While it seems a nice idea, I have a few questions about the execution:
Build and deploy a prototype AI model (e.g., decision tree) on Arbitrum Stylus.
Test performance metrics such as gas usage and inference speed.
Publish a feasibility report.
At the end of phase 2, you mention the publishing of a feasibility report. What would happen if the results so far show that it is not feasible to continue?
Who will decide if it is feasible or not? Is there any external entity taking part in this?
Could you break down the budget/cost to match the implementation steps?
Would you be open to receive the funds as a stream, instead of the full amount upfront?
Stylus's ability to bring Arbitrum closer to a wider pool of engineers and developers is a key competitive advantage for the ecosystem. We believe this inclusivity and versatility will help grow the ecosystem and attract more innovation and we are excited to see initiatives that go in that direction. This is an area where we should continue to invest and promote, as it positions Arbitrum uniquely in the ecosystem by attracting diverse talent and expanding its use cases.
Specifically on this proposal, the use cases you’ve highlighted, particularly around decentralized AI decision-making and smart contract automation, are very interesting. These applications demonstrate the transformative potential of integrating AI directly with smart contracts and showcase Arbitrum's ability to lead in this innovative space.
Stylus's ability to bring Arbitrum closer to a wider pool of engineers and developers is a key competitive advantage for the ecosystem. We believe this inclusivity and versatility will help grow the ecosystem and attract more innovation and we are excited to see initiatives that go in that direction. This is an area where we should continue to invest and promote, as it positions Arbitrum uniquely in the ecosystem by attracting diverse talent and expanding its use cases.
Specifically on this proposal, the use cases you’ve highlighted, particularly around decentralized AI decision-making and smart contract automation, are very interesting. These applications demonstrate the transformative potential of integrating AI directly with smart contracts and showcase Arbitrum's ability to lead in this innovative space.
Because of these, we are generally supportive of the proposal. It balances bold ambition with a practical plan. We appreciate and want to highlight the importance of redirecting funds to other initiatives if the project is deemed unfeasible in Phase 2. It ensures we encourage big ideas, while making sure DAO resources are used effectively.
I’ve seen the Trailblazer AI Grant Program, and it’s a fantastic initiative for supporting AI projects within the community. However, the program has a cap of $10,000 per project, which isn’t sufficient for the scale of our proposal.
I’ve seen the Trailblazer AI Grant Program, and it’s a fantastic initiative for supporting AI projects within the community. However, the program has a cap of $10,000 per project, which isn’t sufficient for the scale of our proposal.
Even if the amount is small, i request you to apply for it so we know that you have passed some basic level of vetting.
Ideally, I would be more comfortable voting for this proposal and the larger amounts if you have already got $10k from the AF and passed their basic screening. Otherwise, I find it hard to trust a team with $200k based on little prior information except a Twitter account that posts about stylus. Even if the idea is good, why are you the best one to implement it?
Have you checked out the Trailbrazer AI Grant Program? The Arbitrum Foundation just announced it.
Introducing the Trailblazer AI Grant Program—a $1,000,000 fund aimed at empowering visionary developers to create cutting-edge AI agents and onchain AI products on Arbitrum chains.
Hey there @0xredacted !
Did you followed what happened in this Stylus hackathon, 2 weeks before devcon, by any chance?
The winning project of the hackathon actually tried to do this. They called themselves The Real Open AI. =)
I have a few questions due to the fact that I am not very familiar with AI and how to use it in crypto. 1.
Here’s the translation，After reviewing the recent updates, I have a few questions:
Suggestions:
• Increase the contingency fund: Consider raising it from $5,000 to $10,000, making it 5% of the total budget, to address potential unforeseen technical challenges or delays.
Suggestions:
• Establish a long-term incentive fund (e.g., $20,000) to support community developers in building open-source tools or extension modules. Additionally, consider hosting activities like regular online/offline workshops or hackathons (in collaboration with EthGlobal) to help developers onboard the framework more efficiently.
• Launch collaborative projects with existing DeFi or NFT initiatives to showcase practical use cases of the AI framework, such as on-chain prediction markets or dynamic NFTs.
Hi @0xredacted, creating useful infra for others wishing to build AI with stylus is a worthwhile pursuit. I agree with your counter-responses that applying for the 10k grants for your endeavour's shape and size is not appropriate.
@AnaTech.eth @aj_eth consider activating Arbitrum to sponsor the above AI Hackathon.
Thank you for the proposal. We find it innovative and believe that, if communicated effectively, it could bring benefits to the DAO. However, we have some observations:
Timelines and budget: If you cannot meet the proposed timelines, will you request additional funding, or will you continue working with the same budget until completion? This should be clarified to ensure that approved proposals are successfully executed.
Amounts in ARB: The amounts are listed in dollars, but it should be specified that they will be paid in ARB, as is standard for all proposals.
Publication of results: Will the results be published on the forum? What is the estimated timeframe for publication upon completion? We suggest monthly updates to keep the community informed and a final evaluation a few months after completion to assess success.
Timeline error: There seems to be an error in the timeline; voting periods start on Thursdays each week.
Thank you for the proposal. We find it innovative and believe that, if communicated effectively, it could bring benefits to the DAO. However, we have some observations:
Timelines and budget: If you cannot meet the proposed timelines, will you request additional funding, or will you continue working with the same budget until completion? This should be clarified to ensure that approved proposals are successfully executed.
Amounts in ARB: The amounts are listed in dollars, but it should be specified that they will be paid in ARB, as is standard for all proposals.
Publication of results: Will the results be published on the forum? What is the estimated timeframe for publication upon completion? We suggest monthly updates to keep the community informed and a final evaluation a few months after completion to assess success.
Timeline error: There seems to be an error in the timeline; voting periods start on Thursdays each week.
We appreciate your attention to these points to strengthen the proposal.
The following reflects the views of the Lampros DAO (formerly ‘Lampros Labs DAO’) governance team, composed of Chain_L (@Blueweb), @Euphoria, and Hirangi Pandya (@Nyx), based on our combined research, analysis, and ideation.
Thank you for putting forward this detailed proposal.
The integration of AI models on-chain using Stylus is a great approach.
The following reflects the views of the Lampros DAO (formerly ‘Lampros Labs DAO’) governance team, composed of Chain_L (@Blueweb), @Euphoria, and Hirangi Pandya (@Nyx), based on our combined research, analysis, and ideation.
Thank you for putting forward this detailed proposal.
The integration of AI models on-chain using Stylus is a great approach.
The project will release open-source tools and developer education materials to empower the broader Arbitrum community.
The emphasis on open-source tools and developer education demonstrates a strong commitment to community building. Have you considered creating beginner-friendly templates, example projects, or a flow to lower the entry barrier for developers unfamiliar with AI or Rust?
Also, would you consider offering developer bounties or hosting competitions to encourage early adoption? We believe incentivizing innovative use cases could rapidly grow the pool of Stylus-based projects.
Conduct a detailed study on the scalability of Stylus for AI models.
We’re interested in learning more about the approach planned for this study. Could you share the specific methodologies or key factors you plan to analyze during this phase? Understanding these details would help clarify how this phase will inform the project’s next steps.
“Your implementation plan is divided into four phases, which looks clear, but I have two questions: 1. In the first phase, you mentioned testing Stylus’ scalability for AI models. If performance or compatibility bottlenecks are discovered, how will the project be adjusted? 2. In the third phase, you plan to optimize the framework and support more complex models within just two months. Isn’t that timeframe too short? Do you have a contingency plan to handle potential delays?
The direction of on-chain AI is indeed cutting-edge, but given the current high demand for DeFi and gaming on-chain applications, does your choice of on-chain AI models have specific use cases to support it? For instance, what scenarios could your decision tree model be practically applied to?
“Your implementation plan is divided into four phases, which looks clear, but I have two questions: 1. In the first phase, you mentioned testing Stylus’ scalability for AI models. If performance or compatibility bottlenecks are discovered, how will the project be adjusted? 2. In the third phase, you plan to optimize the framework and support more complex models within just two months. Isn’t that timeframe too short? Do you have a contingency plan to handle potential delays?
The direction of on-chain AI is indeed cutting-edge, but given the current high demand for DeFi and gaming on-chain applications, does your choice of on-chain AI models have specific use cases to support it? For instance, what scenarios could your decision tree model be practically applied to?
Additionally, if community developers want to build upon this project, do you have any incentive plans, such as hosting hackathons or offering grant rewards?”
Additionally, is there room for budget optimization? For example, the costs for cloud computing and data collection could potentially be reduced by seeking community collaboration, such as partnering with existing Arbitrum projects to share resources and expenses.
This seems like a potentially worthwhile business, at least that's how you're selling it to the DAO. I think you should look at venture funding for something like this rather than asking the DAO. I'll be voting no on this proposal.
Hey there, I agree that Arbitrum with Stylus is in a unique position to enable AI interactions in a much more complete way with respect to other EVMs but I’m not sure how much it makes sense to spend directly for someone to build what you described. Since Arbitrum already has a grants https://x.com/arbitrum/status/1861792767548043430?s=46 for ai development would it just make more sense to add this “on chain model” as an extra bounty to the program?
I feel like even if the idea is in the right direction Arbitrum would benefit more from multiple project submissions instead of a single one under this on chain AI topic.
Hi! the proposal is not bad at all; it is well-intentioned, but I have some questions:
Regarding the initial challenges you mentioned:
Inspired by this, I conducted an experiment deploying a decision tree model using Stylus and Rust, which proved functional but highlighted challenges.
Hi! the proposal is not bad at all; it is well-intentioned, but I have some questions:
Regarding the initial challenges you mentioned:
Inspired by this, I conducted an experiment deploying a decision tree model using Stylus and Rust, which proved functional but highlighted challenges.
It would be helpful if you elaborated on what those challenges were exactly. Were they specific technical limitations, such as gas costs, performance, or compatibility issues with Stylus? A deeper analysis of these problems could not only strengthen the justification for your proposal but also provide clearer direction for the project from the outset.
I understand you are aware of the recent hackathon in Bucharest, but considering that the winning team, "The Real Open AI," attempted to address a similar use case, have you already explored how their approach compares to your proposal? For instance, what tools or models did they use, and what are the key differences in your implementation with:
developing a framework for deploying and interacting with AI models onchain using Arbitrum Stylus and Rust
I am also interested in your approach to zk-Proofs, where you state:
Given the timeline and estimated budget, how do you plan to handle the complexity and cost this entails? Perhaps you could clarify whether this will be an initial implementation or just a research stage within the project. This would help to structure the phases.
Regarding the community, you mention:
The project will release open-source tools and developer education materials to empower the broader Arbitrum community.
This is key to success. But have you considered more proactive strategies to engage the community? Virtual hackathons, rewards for projects using your framework, or collaborations with prominent developers could be excellent ways to increase adoption and the project's impact.
Finally, how do you plan to measure success in the implementation and adoption of these tools by the community? While you mention milestones like the
you could add more specific metrics… such as the number of active developers or projects adopting your framework within a given timeframe
Hello! Thanks for your proposal!
While it seems a nice idea, I have a few questions about the execution:
Hello! Thanks for your proposal!
While it seems a nice idea, I have a few questions about the execution:
Build and deploy a prototype AI model (e.g., decision tree) on Arbitrum Stylus.
Test performance metrics such as gas usage and inference speed.
Publish a feasibility report.
At the end of phase 2, you mention the publishing of a feasibility report. What would happen if the results so far show that it is not feasible to continue?
Who will decide if it is feasible or not? Is there any external entity taking part in this?
Could you break down the budget/cost to match the implementation steps?
Would you be open to receive the funds as a stream, instead of the full amount upfront?
Stylus's ability to bring Arbitrum closer to a wider pool of engineers and developers is a key competitive advantage for the ecosystem. We believe this inclusivity and versatility will help grow the ecosystem and attract more innovation and we are excited to see initiatives that go in that direction. This is an area where we should continue to invest and promote, as it positions Arbitrum uniquely in the ecosystem by attracting diverse talent and expanding its use cases.
Specifically on this proposal, the use cases you’ve highlighted, particularly around decentralized AI decision-making and smart contract automation, are very interesting. These applications demonstrate the transformative potential of integrating AI directly with smart contracts and showcase Arbitrum's ability to lead in this innovative space.
Stylus's ability to bring Arbitrum closer to a wider pool of engineers and developers is a key competitive advantage for the ecosystem. We believe this inclusivity and versatility will help grow the ecosystem and attract more innovation and we are excited to see initiatives that go in that direction. This is an area where we should continue to invest and promote, as it positions Arbitrum uniquely in the ecosystem by attracting diverse talent and expanding its use cases.
Specifically on this proposal, the use cases you’ve highlighted, particularly around decentralized AI decision-making and smart contract automation, are very interesting. These applications demonstrate the transformative potential of integrating AI directly with smart contracts and showcase Arbitrum's ability to lead in this innovative space.
Because of these, we are generally supportive of the proposal. It balances bold ambition with a practical plan. We appreciate and want to highlight the importance of redirecting funds to other initiatives if the project is deemed unfeasible in Phase 2. It ensures we encourage big ideas, while making sure DAO resources are used effectively.
I’ve seen the Trailblazer AI Grant Program, and it’s a fantastic initiative for supporting AI projects within the community. However, the program has a cap of $10,000 per project, which isn’t sufficient for the scale of our proposal.
I’ve seen the Trailblazer AI Grant Program, and it’s a fantastic initiative for supporting AI projects within the community. However, the program has a cap of $10,000 per project, which isn’t sufficient for the scale of our proposal.
Even if the amount is small, i request you to apply for it so we know that you have passed some basic level of vetting.
Ideally, I would be more comfortable voting for this proposal and the larger amounts if you have already got $10k from the AF and passed their basic screening. Otherwise, I find it hard to trust a team with $200k based on little prior information except a Twitter account that posts about stylus. Even if the idea is good, why are you the best one to implement it?
Have you checked out the Trailbrazer AI Grant Program? The Arbitrum Foundation just announced it.
Introducing the Trailblazer AI Grant Program—a $1,000,000 fund aimed at empowering visionary developers to create cutting-edge AI agents and onchain AI products on Arbitrum chains.
Hey there @0xredacted !
Did you followed what happened in this Stylus hackathon, 2 weeks before devcon, by any chance?
The winning project of the hackathon actually tried to do this. They called themselves The Real Open AI. =)
I have a few questions due to the fact that I am not very familiar with AI and how to use it in crypto. 1.
I have a few questions due to the fact that I am not very familiar with AI and how to use it in crypto. 1.
What does this mean? Scalability in what sense, I did not quite understand what the result should be. 2.Identify the most suitable lightweight AI models for deployment
What are the options, how can we use AI models in our case? 3.
Arbitrum does not have this now, why do we need to do this here? 4.Optimize the framework for larger datasets and more complex models
That is, our task is to create a framework for creating AI? I just did not find this in the text earlier.
Standard questions about the budget:
I have a few questions due to the fact that I am not very familiar with AI and how to use it in crypto. 1.
What does this mean? Scalability in what sense, I did not quite understand what the result should be. 2.Identify the most suitable lightweight AI models for deployment
What are the options, how can we use AI models in our case? 3.
Arbitrum does not have this now, why do we need to do this here? 4.Optimize the framework for larger datasets and more complex models
That is, our task is to create a framework for creating AI? I just did not find this in the text earlier.
Standard questions about the budget:
