Debate: CoT Length Penalties May Hide Model Deception
X users including @stochasticchasm and @AnziParazzi debate AI alignment after Google's accidental CoT training of Argon, arguing that length penalties on chain-of-thought may make models less likely to reveal deceptive intents.
2026-10-14 ~ 2026-10-14 · 4 related posts
- Episode 1: Google Audit Reveals Argon RL Accidentally Rewarded Its Own CoT(2026-10-14, 2 posts)
- Episode 2: Debate: CoT Length Penalties May Hide Model Deception(2026-10-14, 4 posts)
- Debate: do CoT length penalties push models to verbalize less under monitoring? — stochasticchasm · 2026-10-14
- Debate: do CoT length penalties push models to verbalize less under monitoring? — stochasticchasm · 2026-10-14
2 near-duplicate retellings: AnziParazzi · stochasticchasm