Shauli Ravfogel reposted
LLM introspection revisited. if we do the controls properly we may not have strong enough evidence just yet arxiv.org/html/2605.26...
Who's Who of AI
Shauli Ravfogel
Faculty fellow at NYU CDS. Previously: PhD @ BIU NLP.
What they're sharing
Can LLMs Introspect? A Reality Check arxiv.org
View on Bluesky →
Can LLMs Introspect? A Reality Check arxiv.org
Articles & links
12/ We just think the evidence so far doesn't quite support a strong interpretation of the introspection findings in previous work. And, as always, extraordinary claims require extraordinary evidence. Paper: arxiv.org/abs/2605.26242
Their own posts
Recent commentary
1/ Can LLMs introspect, i.e., reason about their internal states? Recent work claims LLMs notice when their "thoughts" get tampered with, and can report the content. We took a closer look and think it's too early to say that. Work led by Shashwat Singh, with @tallinzen.bsky.social and me. A thread 🧵
Their network
In Shauli Ravfogel's orbit
Center = Shauli Ravfogel. Left = members they follow (green edges). Right = members who follow them (blue edges). Top = mutual follows (orange edges, slightly larger). Drag any node to reposition; click to open that profile.