AI research and discussion on LessWrong. www.lesswrong.com
Shows LLMs in realistic hiring show race and gender bias while their chain-of-thought never verbalizes it, so CoT monitoring misses it; ablating demographic directions reduces the bias where prompting fails.
Reviews recent latent-reasoning and diffusion LLM architectures, assessing how each threatens legible chain-of-thought as an alignment and interpretability tool and whether any preserve human-readable reasoning.
Argues that latent continuous-thought reasoning like COCONUT could undermine chain-of-thought monitoring and oversight, and surveys responses including avoiding it, regulation, and interpreting latent states.