Internal Codex version found the same counterexample in a proof attempt
aaron_lou · x · 2026-07-21
A thread sharing a writeup from an internal version of Codex says the model found essentially the same counterexample that Levent discovered, even without web search.
The post frames this as a useful internal proof attempt: the model produced a clean summary of the strategy, and the author highlights the result as a noteworthy capability signal for Codex-style systems.
More from Models
- Claim says Kimi was distilled from Fable, sparking a model-attribution jab — cephaloform · 2026-07-22
- Gary Marcus says LLM math skills are like knowing only a car’s engine size — GaryMarcus · 2026-07-22
- OpenAI’s Codex + GPT-5.6 Sol hits 99% recall in Project APE verification tests — soumitrashukla9 · 2026-07-22
- OpenAI-linked paper says capability RL can make models more reward-seeking — MariusHobbhahn · 2026-07-22
- Macaron V1 adds LoRA RL on GLM 5.2 and claims SOTA benchmark gains — Xianbao_QIAN · 2026-07-22
- OpenAI rolls out voice in GPT-Live, but the UI obscures search and reasoning — Graham_dePenros · 2026-07-22