Abstract:We report an experiment in autoformalisation of Gödel's second incompleteness
theorem in Agda using Claude. The theorem is formalised for Church's Basic Recursive
Arithmetic, following the proof outline given in Guard's 1963 lecture notes. The
entire Agda development, comprising approximately 50,000 lines and containing no
postulates, was produced through interaction with Claude; the author did not write
any Agda code.
Beyond the formalisation itself, the project provides a case study of the strengths
and limitations of current large language models in mathematics. An initial
autonomous attempt based on a paper of Rose failed because of a false Lemma;
the resulting formal development produced by Claude established a statement
superficially resembling Gödel's theorem but mathematically unrelated to it. This
failure was traced to an insufficient specification of the internal provability
predicate, illustrating how an LLM may reason correctly from an incorrect formal
specification.
The final development follows Guard's proof and required the reconstruction of several
implicit mathematical arguments, including the role of the internal numeral-encoding
operation and the specification of substitution. The
resulting formalisation clarifies a number of details left implicit in the original
presentation and provides a fully machine-checked proof of Gödel's second
incompleteness theorem for Basic Recursive Arithmetic.
From: Thierry Coquand [view email]
[v1]
Mon, 1 Jun 2026 08:39:20 UTC (21 KB)
[v2]
Tue, 2 Jun 2026 04:56:29 UTC (21 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。