Dietterich: Lean-checked LLM proofs are not mere interpolation
Thomas Dietterich argues that Lean proof checkers give LLMs access to external information, and even if the checker is internal, the computation merely makes implicit knowledge explicit rather than interpolating existing data.
2026-10-11 ~ 2026-10-11 · 2 related posts
- Dietterich: Lean proof checker feeds LLMs new info, so proofs aren't interpolation — tdietterich · 2026-10-11
- Dietterich: even with Lean checker inside the system, LLM proofs aren't interpolation — tdietterich · 2026-10-11