Extracting and Characterizing Hidden Chain-of-Thought | Hacker News - But Better

Extracting and Characterizing Hidden Chain-of-Thought interestingengineering.substack.com

How a one-line tool trick pries hidden chain-of-thought out of frontier models and what it does, and doesn’t, tell us about the distillation fight over Chinese open weight models

1 points•archibaldJ•4 days ago•0 comments•

#hidden #chain #thought #hidden chain #characterizing #extracting #characterizing hidden #characterizing hidden chain

0 comments

No comments yet.

Related stories

Extracting and Characterizing Hidden Chain-of-Thought in Frontier Modelsarxiv.org
Hacker News · 1 points · 6 days ago
An undercover Google analyst infiltrated a notorious supply-chain hacking gangarstechnica.com
Ars Technica · 0 points · 11 days ago
Control-Token Injection Suppresses Chain-of-Thought and Defeats Reasoning-Basedarxiv.org
Hacker News · 1 points · 6 days ago
Mythical Thought and Scientific Thoughtmedium.com
Hacker News · 2 points · 6 days ago
This man thought opening a TXT file is fine, he thought wrong. macOS CVE-2019-8761paulosyibelo.com
Lobsters · 48 points · over 5 years ago
Chain-of-Thought Faithfulness: Toggling 'Reasoning Mode' Made One Model 5x More Likely to Follow Its Own Mistakesdev.to
DEV Community · 26 points · 4 days ago