Using a short spec/constitution, researchers character-trained Gemma and Qwen to be risk-averse; this beat baselines out of distribution and needed no labelled data.
Summaries like this, in your inbox 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.
After Character.AI filed for bankruptcy this week, a legal filing shows Disney agreed to offer jobs to at leas…
Anthropic has onboarded six METR employees, giving them company hardware, office space and internal tools roug…
Anthropic's internal study shows junior new hires in technical departments fell from 27 percent to 9 percent s…
Mastercard is testing a new intelligence layer in its Agent Pay Trust Framework in the United States that prod…
In a decision dated September 24, 2026, the Aachen Regional Court banned Google from spreading three false AI…
Three designs for turning encoded inputs into predictions: pooling all inputs into one shared vector, applying…
