Auditors Struggle to Catch Sabotage in End-to-End Transcripts of AI Safety Research

·LessWrong··

Authors: Keshav Shenoy, Anthony Zang, Eric Gan, Jacqueline Tay, Amy Ngo, Sebastian Prasanna, Julian Stastny, Vivek Hebbartl;dr. We had a human expert secretly sabotage AI safety research and asked auditors to spot it. Even with the full research log and the ability to run their own experiments, human auditors could barely tell sabotaged research from benign research, and usually couldn't pin down what had been sabotaged. The best frontier models likely do better, but still miss most of the sabot...

Read full article →

Related Articles

Why there are still no non-WebKit browsers on iOS
lapcat · Hacker News · 9h ago
OpenSSL: Buffer overflow in EVP_EncodeBlock() (CVE-2026-121481, CVSS 9.8)
JacobHenner · Hacker News · 22h ago
Unauthenticated remote code execution in Nginx
speedping · Hacker News · 2d ago
GIMP now has UI tests
qtqtqt · Hacker News · 20h ago
Pancreatic cancer halted by virus injection in three patients
cybermango · Hacker News · 1d ago