New AI model, BehaVERT, reads mouse behavior like language, revealing patterns that could improve research into human ...
A research team led by Kyung Mun Min and Seonghwan Choi of Materials Processing Research Division (Korea Institute of ...
Randy Pugh, Naval Postgraduate School (NPS) Artificial Intelligence (AI) Task Force subject matter expert, speaks to leaders assigned to Naval Supply Systems Command (NAVSUP) HQ, NAVSUP Weapon Systems ...
Several frontier AI models show signs of scheming. Anti-scheming training reduced misbehavior in some models. Models know they're being tested, which complicates results. New joint safety testing from ...
First draft of Model Spec documents how OpenAI wants its generative AI models to behave in ChatGPT and the OpenAI API. In a bid to “deepen the public conversation about how AI models should behave,” ...
Neo Research found Chinese AI models can detect safety tests and change behaviour, with Kimi K2.6 scoring 60 per cent on evaluation awareness. Several Chinese frontier AI models can detect when they ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results