Do OpenAI's math-proof agents call a Lean verifier at inference time?
yoavgo · x · 2026-09-27
Yoav Goldberg raises an open technical question: do the math-proof agents at OpenAI and similar labs run inside a harness that calls a Lean verifier every few steps, or is Lean used mainly in training with inference relying on learned behavior? He assumes the former, but it's not publicly known — with implications for whether formal verification serves as a runtime guarantee or just a training signal.
More from coding & agent
- Creator spends $3,000 remaking 301 viral video effects with Claude Opus 5.5, open-sources all prompts — yihui_indie · 2026-09-27
- 282 viral Claude Opus 5.5 videos with exact prompts open-sourced on GitHub — yihui_indie · 2026-09-27
- Who is building an agent-first programming language optimized for correctness, not humans? — burny_tech · 2026-09-27
- Researcher says he now drives desktop AI agents with a game controller and voice — hugobowne · 2026-09-27
- Gary Bernhardt: Assembly will never be a good language for AI agents — mgill25 · 2026-09-27
- OpenAI L7 engineer says firm can't build IP-whitelisted egress VLAN, experts say IP allow-lists are obsolete — arthurcolle · 2026-09-27