Cross-Dataset Transfer Evaluation of Deception Probes in Smaller Models

·LessWrong··

SummaryRecently, Apollo Research tested whether linear probes could identify honest and deceptive responses from Llama-3.3-70B-Instruct and reported AUROC values between 0.96 and 0.999. To test some of their claims, I used the scores Apollo released to recalculate the nine values they published, reproducing them exactly.I used the same method on five smaller open models, each having between 1 billion and 9 billion parameters. Each probe was trained on one deception dataset and tested on the othe...

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