I'm seeing a lot of euphoria about how Opus 5.5 is good at TLA+, and this means that all software will soon be formally verified. As a person who loves TLA+ so much he wrote a book on it, I want to throw a particular cold shower on people's enthusiasm by talking about the limits
Beginning to think that when my coding agent says some effort is "~2-3 days" that means it'll take 2-3 days for me to discover & fix missed edge-cases, not that it'll take 2-3 days to implement
Formal methods are getting trendy, which is a really good thing.
Quick explainer: model-checking formal methods describe a system as a state machine (currentState + event → nextState).
That gives you a graph of possible behaviors. Then you can check properties on every path.
I used Opus 5.5 to formally verify the Claude Agent SDK using Lean. A couple short prompts = 16 PRs fixing various bugs and race conditions. Video attached.
TLA+ also works well. I sometimes combine Lean and TLA+ to look for issues around data flow, concurrency, and state mgmt.
