"Anthropic’s “Hot Mess” paper overstates its case (and the blog post is worse)" by RobertM

LessWrong (Curated & Popular) • February 04, 2026 • Solo Episode

Guests

No guests identified for this episode.

Description

Author's note: this is somewhat more rushed than ideal, but I think getting this out sooner is pretty important. Ideally, it would be a bit less snarky. Anthropic[1] recently published a new piece of research: The Hot Mess of AI: How Does Misalignment Scale with Model Intelligence and Task Complexity? (arXiv, Twitter thread). I have some complaints about both the paper and the accompanying blog post. tl;dr The paper's abstract says that "in several settings, larger, more capable mod...

Audio