←
Max Feldman21 posts
Max Feldman avatar

Max Feldman

@_maxfeldman

numbers guy building with YC F26

◷ Joined April 2021▧ 1 Photos and videos
Shayan | Repovive (YC F'26) avatar
⟳ Max Feldman retweeted
Shayan | Repovive (YC F'26)@ShayanCJahan·Nov 16

Repovive is scaling AI formal verification for the chips and critical software the world runs on. The team includes Olympiad medalists, former frontier lab members, PhD researchers, and former Google engineers. Repovive has contracts with AI labs to improve models’ formal verification capabilities and is backed by investors from OpenAI, Anthropic, xAI, Cognition, and many other companies. Repovive has a talent-dense community of 12,000 IOI and IMO participants. Formal proofs can establish that a system meets its specifications, but finding those proofs still takes specialized expertise and substantial manual work. Teams often rely on tests that cover specific scenarios, leaving gaps where failures can go undetected. Today, Repovive provides AI labs with formalization data and reinforcement learning environments for model training and evaluation. Its non-public Lean tasks come with formally verified reference proofs, giving labs difficult problems for training and a rigorous way to evaluate whether models can solve them. The long term vision is to make formal verification practical enough to become a standard step in chip design, critical software development, and mathematical research.

1:07
Max Feldman avatar
Max Feldman@_maxfeldman·Nov 2

Excited to share that @asherdfeldman and I won first place overall at the Vibecheck formal methods hackathon yesterday! Had a great time meeting super cool people and learning from everyone there. We built Sound and Complete, a verified tool to help guitarists practice call-and-response blues. Thanks to @maxvonhippel, @qd_forall and everyone else who helped put on this fantastic event! There are some large winds and great people moving FM forward, excited for what is to come!

Post attachment
Aneesh Kethini avatar
⟳ Max Feldman retweeted
Aneesh Kethini@aneeshkethini·Oct 29

Today we’re launching Hue (YC F26). We give your agent a simulated version of the environment it works in, so you can test changes in realistic worlds and ship with confidence.

1:35
Max Feldman avatar
Max Feldman@_maxfeldman·Oct 26

First they ignore you, then they laugh at you, then ...

Rumor is P = NP, specifically there is a promising route to 3-SAT in O(n^{808017424794512875886459904961710757005754368000000000})

Joscha Bach avatar
⟳ Max Feldman retweeted
Joscha Bach@Plinz·Oct 26

What?! P might equal NP after all...

The computer science collaboration will understand and explain a result concerning the Exponential Time Hypothesis (ETH), a longstanding conjecture about the computational complexity of Boolean formula satisfiability, a problem deeply related to the P vs. NP problem. Surprisingly, our system has recently proved that the ETH is false, a result that was subsequently verified in Lean. The refutation of the ETH reopens questions about how much faster these tasks could become, and may help guide the search for better algorithms. Finding such algorithms, and turning theoretical advances into practical improvements, will require significant further research. Our system found its natural language disproof for the ETH we reached out to to @rrwilliams. Ryan will form a collaboration with Russell Impagliazzo and Ramamohan Paturi to verify and shepherd this result. Impagliazzo and Paturi, along with Francis Zane, are the original proposers of the Exponential Time Hypothesis, and Williams has refuted strong versions of the ETH, used ETH for hardness results, and connected algorithms and lower bounds. This group asked us to make all raw data of the results public to facilitate independent verification by the community, which we have done by posting the natural language proof and Lean formalization to our GitHub repo. The group also invites the community to help organize an open examination of the ETH claim and to discuss the broader questions that AI-generated breakthroughs raise about verification, access, credit, and the future of research. github.com/openai/math/blob/…

Max Feldman avatar
Max Feldman@_maxfeldman·Sep 16

Rumor is P = NP, specifically there is a promising route to 3-SAT in O(n^{808017424794512875886459904961710757005754368000000000})