Overthinking: Amplifying reasoning weights makes models reveal their secrets

·LessWrong··

If you take the weight difference between a reasoning model and its non-reasoning instruct counterpart, and then apply more of that difference to the reasoning model, you get what we call an overthinking model. Overthinking models are usually worse at keeping secrets. This is good, because models should (generally) be prevented from keeping secrets in alignment audits. Across four model organisms with hidden information (2B–32B), amplifying the reasoning direction surfaces secrets up to 10× more...

Read full article →

Related Articles

Unauthenticated remote code execution in Nginx
speedping · Hacker News · 6h ago
Highly classified US national security communications network goes down
monkeydust · Hacker News · 1d ago
Harvard researchers find AI coding agents shifted the bottleneck to code review
judahmeek · Hacker News · 1d ago
New Evidence Shows School Phone Bans Are Gradually Improving Test Scores
donohoe · Hacker News · 1d ago
Java4Shell: RCE in OpenJDK when processing Base64
werrett · Hacker News · 1d ago