Lean AI proofs to ZFC: researcher says translation is feasible, with caveats
jessi_cata · x · 2026-09-11
jessicata raises a concrete, testable question: to what degree do typical Lean AI results translate to ZFC, and how feasibly.
- Potential issues include Lean soundness bugs and Lean proofs possibly relying on strong axioms in practice.
- The author guesses Lean-to-ZFC translation mostly works: with a lab team on it, translating existing artifacts (e.g. the Navier-Stokes formalization) would likely not be very hard, resembling translation between programming languages.
- A discussion of reliability and generality of AI-produced formal proofs.
Related event: Can Lean AI Proofs Be Translated to ZFC?(2 posts)→
More from Research
- DeepMind researcher: all of mathematics will soon be formalizable, with agents hunting proofs — ChrSzegedy · 2026-10-28
- A fine-tuned 'cat obsession' control fools every AI welfare criterion — MirrorEthic_Anchor · 2026-10-28
- Sweeping every Qwen3-8B neuron, rated for weirdness by Haiku — Sauers_ · 2026-10-28
- Kevin Buzzard: Lean formalization revealed errors in theorems by 4 Fields medalists — Machine Learning Street Talk · 2026-10-28
- Follow-up repo machine-verifies Hamiltonian cycle results on top of OpenAI/Anthropic ETH refutation claims — xennygrimmato_ · 2026-10-28
- DiscoTrace wins EMNLP 2026 Best Paper: LLM answers lack humans' community-specific rhetorical diversity — TuhinChakr · 2026-10-28