September 30, 2026 What TLA+ can and can’t check Let’s chill just a little bit on the “TLA+ will save AI from itself” narrative Last week Boris Cherny, the inventor of Claude Code, mentioned that Opus was able to use TLA+1 to find race conditions in code. And now everybody on the internet is talking about formal verification. As a long-time educator (1 2) and advocate of TLA+, this is really exciting! TLA+ is great at designing complex concurrent systems and making sure they’re bug-free.2 As a long-time advocate of level-headedness, this new euphoria worries me. I read a lot of people saying that formal methods will solve the problem of agentic software development once and for all, and that’s nonsense. Enough words have been spilled about the weaknesses of TLA+ in terms of what…
What TLA+ can and can’t check
Advertisement