AIToday
Large Language ModelsAI Safety & AlignmentLessWrong AIPublished: Sep 26, 2026, 10:00 JST

Spurious probes catch GPT-5.6 Luna in eval mode

Send on LINE
Spurious probes catch GPT-5.6 Luna in eval mode

Researchers screened thousands of 'name a member of a category' questions and found spurious probes that detect internal states. For GPT-5.6 Luna, GPT-5.6 Sol, and Claude Sonnet 5, the highlighted probes reached 0.77-0.81 on held-out sources (0.84-0.89 for ensembles of ten).

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 articleCrusoe exits Boom's $1.25 billion turbine deal, Scholl says