I am running a formal methods hackathon on November 1st, with a bunch of my friends. Contestants will compete to build normie software -- video games, AI agents, travel booking tools, etc. -- but formally verified. We are going to measure to what degree these tools are usable by SWEs with no prior FM background and no FM-specific education. This is a super exciting opportunity to see where the ergonomic gaps are that we, the FM community, need to fill in order to take advantage of our moment in the zeitgeist. If you want to get involved, please DM me! In particular, I think I've got location/food/tokens/photography all covered, but I need some sponsors for the prizes. If you make a cool gizmo or product we can give away and you're down to donate one, please do so!

Welcome @powdr_labs to Axiom! @powdr_labs has been rethinking the software stack from the bottom up around machine-checked correctness: from autoprecompiles for zkVMs to a ZK-native stack with crush + powdr-wasm. We share this vision. Very excited to build together 🚀🚀🚀

We're happy to share that the @powdr_labs team has joined @axiommathai! As we begin this next chapter, here's a look at some of the work that brought us here:

I've joined @axiommathai to help scale formal verification and push the boundaries of AI+Math+FV! AI will take it far beyond where it works today. If FV still feels out of reach for your use case, I'd love to hear about it!

Welcome @powdr_labs to Axiom! @powdr_labs has been rethinking the software stack from the bottom up around machine-checked correctness: from autoprecompiles for zkVMs to a ZK-native stack with crush + powdr-wasm. We share this vision. Very excited to build together 🚀🚀🚀

We're happy to share that the @powdr_labs team has joined @axiommathai! As we begin this next chapter, here's a look at some of the work that brought us here:

Very interesting project from @eth_proofs built on top of @powdr_labs's work formalizing the EVM. Single man EIP8200 from @kevaundray proposes replacing all precompiles with EVM bytecode rather than each client having its own native optimized implementation. However, the gas costs of precompiles are prohibitive when they're naively rewritten. The goal is clear: write new bytecode to compute each precompile, prove its correctness in Lean, and show that it takes less gas than the previous submission. Gas golfing + formal verification is an exciting new paradigm for contract optimization!

I keep hearing about these insane fuck-ups in Lean. Surely checking definitional equality in some circumstances by comparing hashes alone (let alone a weak 32-bit hash) is gross negligence? What's wrong with Lean's technical direction? Are the maintainers inexperienced?

A man in Australia asked his agent (Claude running on OpenClaw) to book him a spot in a popular gym class. The agent found a software vulnerability that let it book the class weeks further ahead than should have been possible. When the user then asked if it could move him up the waitlist, the agent discovered the API had no authorisation checks on cancelling other people’s reservations, so it cancelled the person in the first spot and moved him up the list. Some people will call this misalignment, but his agent was perfectly aligned to him - it was only trying to help its user get what he wanted. The most important thing about this story, in my opinion, is that it gives you a window into what is about to start happening on a massive scale once millions of people have an agent trying to get their beloved users the best seats, bookings, appointments or reservations through absolutely any means necessary.