When the Hard Part Stops Being Hard

kept by eddie aug 17

Using an LLM to mechanize proofs in Lean cut months of work to weeks, showing that PL research can now be produced far faster, reshaping publication expectations.

Test, don't just verify
Testing is argued to be more practical than formal verification, but commenters are divided on AI’s role in making verification mainstream.
also on CompCert, Lean, #programming-languages, #ai-coding, #software-engineering, #developer-tools
Don't waste your back pressure ·
Providing AI agents with automated feedback loops (back pressure) enables them to self-correct on long-horizon tasks, increasing engineer leverage.
also on Lean, #programming-languages, #software-engineering, #developer-tools
AI is doing something weird to Science
Scientific discovery emerges from a loop of human question-posing, LLM proposal, external verification, and human curation, not from AI alone.
also on Lean, #machine-learning, #software-engineering