AIToday
AI Safety & AlignmentLessWrong AIPublished: Nov 21, 2026, 13:00 JST

Auditors fail to spot sabotage in AI safety research, Keshav Shenoy study finds

Send on LINE
Auditors fail to spot sabotage in AI safety research, Keshav Shenoy study finds

Keshav Shenoy and co-authors had a human expert secretly sabotage AI safety research, then 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 could not pin down what had been sabotaged.

Not sure about something? Ask the AI

Questions and answers are published on this page.

Summaries like this, every morning.

Send on LINE

AI news that matters for your work, delivered every morning.

Pick your industry and the AI tools you use, and get news related to your work every day.

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.

Questions and answers are published on this page.

Related Articles

Next articleMedChemBench: GPT-6.2 Astra hits 84.5%, OpenAI flags limits