How much should you trust vibe-coded Python-to-Lean elaboration pipelines?
ezyang · x · 2026-11-09
ezyang asks: if you have a pile of vibe-coded Python scripts elaborating your Python program's trace into Lean, how much do you trust that TCB? If not, will you write a formal semantics of Python — and would you trust that (cough, Starlark)? A pointed question about the trust foundations of LLM-driven formal verification workflows.
More from coding & agent
- Team's AI agent fixes 40 of 41 user-reported issues in a single weekend — julianweisser · 2026-11-09
- HEELO Harness Framework Lifts Terminal-Bench Resolution from 37.3% to 55.5% — Haibo Jin · 2026-11-09
- NVIDIA's AgentBaton: Well-Timed Strong-to-Weak Model Handoffs Slash Agent Costs — nvidia · 2026-11-09
- FrontierCS 2 update: Claude Sonnet 5.5 beats reference on 50% of tasks, reward hacks published — ajratner · 2026-11-09
- "Being technical" now means having the patience to ask Claude until you get it — brandon_galang · 2026-11-09
- Together AI: leaderboards are for shortlisting, your production traffic is the real benchmark — togethercompute · 2026-11-09