New on our Frontier Red Team blog: using Claude to formally verify software at large scale.
Formal verification can prove that code is free of certain bugs, but historically it has only been feasible for small codebases (or required a lot of expert time).
With AI models, however, this is beginning to change. In collaboration with @theoremlabs, we used Claude to prove security properties in over one hundred real-world open-source libraries over the span of a few weeks.
Read our research in full here: https://t.co/zUyx8CjBEk
@theoremlabs Congrats, an important step for formal verification. The opportunity ahead is enormous: bringing rigorous guarantees to the software being built at AI speed. We're just getting started
We have heard so many debates about the future of #programminglanguages back at @Techweek_ and also many events were encouraging the usasge of #rust.
So here is our small contribution to your general knowledge about rust.
Disclaimer: not a coding advice😉
We’re releasing a broad range of new mathematical results produced by an internal frontier model.
We’ve been consulting with the independent Advisory Group on Mathematics and Artificial Intelligence at the Institute for Advanced Study, and we have drawn on their advice and public recommendations to inform how we release these results.
https://t.co/7N6TPlft1P
Most proofs languages are also programming languages. The reason is you need ways to define functions to reason, and from there you can define programs. Rocq can compile to OCaml for example.
I think it is still better to separate proof and program languages though, as the design spaces are a bit different, and then you can optimize the two independently.
we see a big debate, all over X 🔥 on what #theorems are used for #formalverification. so here we have prepared something small 👉 for you to learn more 🍈🍈🍈
Many debates today about #TLA+, following @bcherny's tweet.
TLA+ stands for Temporal Logic of Actions, a specification & architecture modeling language.
Check our diagram below to understand formal families 👨👩👧👦 and how they are used 👉
we are delighted to see @bcherny's update & #formalverification (we're working so hard on building) getting momentum!!!
PS: to ensure #correctness of your AI generated code / agent & its logic, you will need more than #lean SDK & skilful use of @claudeai 👌
For Navier-Stokes and upcoming conjectures, this is leading to a lot of work to verify theorems provers and some people are worried the AI found a breach in them.
But the formalization was the last step of the process, so I believe the proofs are right.