The Blind Spot of AI Formal Proofs: Natural Language and Lean Semantic Alignment
AlexKontorovich · x · 2026-07-25
Alex Kontorovich adds a crucial caveat to the trust in formal proof checkers like Lean. He points out the need to verify that Lean statements and definitions actually align with the intended natural language proofs. This "semantic alignment" problem cannot be solved purely computationally.
More from AGI Musings
- AI folks, stop saying "biology" when you mean drug development — KevinKaichuang · 2026-10-26
- Anthropic: junior tech hires fell from 27% to 9% as agent hours hit 6x employee hours — thione · 2026-10-26
- Anthropic's Jascha: you may have only 1–5 years of intellectual contribution before AGI — GabGarrett · 2026-10-26
- Anthropic's S-1 Shows $6.6M Revenue Per Employee as AI Agents Log 6x Human Hours — jacalulu · 2026-10-26
- Ben Recht: The world needs a truly open language model, and it's easier to build than you think — beenwrekt · 2026-10-26
- Which jobs fall to AI first? The rule: any layer whose rules can be written as code — FinanceYF5 · 2026-10-26