Kaley Brauer 💫(@kaleybrauer):If you ask a frontier LLM a multi-hop reasoning question, e.g., "Who won the Nobel Prize for Chemistry in (1900 + Mozart's age when he died)?", it usually can't answer correctly immediately (no thinking) BUT if you ask the same question & append 300 dots, suddenly it can answer?

Kaley Brauer 💫

@kaleybrauer

@NSF physics postdoc fellow at @Harvard, AI safety fellow at CBAI丨physics PhD @MIT 🌌💃🦆

가입 February 2010

884 팔로잉 중 5.9K 팬

Kaley Brauer 💫@kaleybrauer

2026.07.17 18:31

If you ask a frontier LLM a multi-hop reasoning question, e.g., "Who won the Nobel Prize for Chemistry in (1900 + Mozart's age when he died)?", it usually can't answer correctly immediately (no thinking) BUT if you ask the same question & append 300 dots, suddenly it can answer?