
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.
Summaries like this, 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 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.
Levent Alpöge published a 4-page remark.pdf saying he believes he found a Riemann Hypothesis proof with Claude…

MetAI published the five-block structure of its AI育成プログラム for companies, schools and local governments, coveri…

The Elders published a "Humanity Threshold" declaration dated 16 July 2026 calling for a treaty that would bar…

METR released Time Horizon 1.1, expanding its benchmark from 170 to 228 tasks and scoring judgment-heavy work…

In its 2026 sustainability report, Meta said it is re-evaluating the 2030 timeframe for its net-zero goal, aft…

American Banker published exclusive research examining how JPMorgan's AI strategy is putting governance to the…
