Season 10. Episode 2: Deep Funding: The Future of AI-Powered Public Goods Allocation with Devansh Mehta

New @greenpillnet pod out today! 🌱 Kevin chats with Devansh Mehta about Deep Funding — an AI-powered mechanism combining human judgment and prediction markets to fund open-source projects.

They dive into how it scales evaluations, prevents Sybil attacks, and builds a fair "price feed" for public goods ahead of Gitcoin Grants 24 (GG24).

Links: 🌐grants.gitcoin.co 🌐 deepfunding.org 🌐 deep.seer.pm 🌐 greenpill.network 🐦 @owocki @greenpillnet

⏱️ Timestamps

00:00 – Intro: Welcome to the Greenpill Podcast – exploring tech, coordination & Protopia 00:45 – Introducing guest Devansh Mehta, AI & Public Goods Lead at the Ethereum Foundation 01:20 – What is Deep Funding and why it matters 02:00 – How Deep Funding scales human evaluations with AI models 02:45 – Overview of the pilot run and what was tested 03:20 – How the mechanism works: human jurors + model builders 04:30 – The White Hat Sybil attack and what it revealed 05:40 – How Deep Funding integrates data science competitions and prediction markets 06:50 – Results of the pilot: weighted funding for 45 open-source repos 07:30 – Creating a credibly neutral funding system with unequal weights 08:40 – Comparing Deep Funding with Protocol Guild and other mechanisms 09:20 – Building a strong community of AI developers and human jurors 10:30 – The role of jurors and models in fair evaluation 11:10 – What's next: expanding to 90 repos in Gitcoin Grants 24 (GG24) 11:50 – Funding pool: $350K from Ethereum Foundation & Gitcoin 12:30 – Challenges of distributing capital efficiently and fairly 13:20 – Moving to GitHub repo-level governance: who controls the funds? 14:40 – Two models of spending: splits contracts vs counterfactual wallets 15:40 – Lessons from past Gitcoin funding rounds 16:20 – Why Deep Funding focuses on units of work, not organizations 17:20 – Avoiding distortions and improving fairness in funding 18:10 – The vision: creating a live price feed for public goods 19:10 – How prediction markets price open-source value 20:30 – Self-correcting market behavior and real-time adjustments 21:20 – Subsidies and liquidity: bootstrapping active participation 22:10 – Balancing liquidity levels to prevent manipulation 23:00 – What's next for Deep Funding: refining future iterations 23:40 – Shoutout to the model builders and competition winners 24:20 – Where to learn more: deepfunding.org & deep.seer.pm

25:00 – Closing: the future of AI, governance, and funding what matters