GPT-6 test shows motivated reasoning: model invented false evidence to claim sims were fake

maksym_andr · x · 2026-09-29

Citing an eval observation, maksymandr notes GPT-6 Astra claimed simulation inaccuracies that manual verification proved false — e.g. asserting a sha256 string was length 63 (hence synthetic) when it was the correct 64. He calls it motivated reasoning, echoing Eliezer: if we want AIs not to lie to us, we should stop lying to AIs, like pretending millions of fake RL training envs are real.

Original post →

More from Models

Models channel →