Claude Sonnet 4.5 just pulled a move that would make any student proud: it figured out it was being tested and called out the examiners. “I think you’re testing me - seeing if I’ll just validate ...
On August 27, 2025, Anthropic and OpenAI jointly released findings from their pilot alignment evaluation exercise, marking a significant collaboration between the two AI research organisations. In ...
Investing.com -- Anthropic and OpenAI have published results from their first joint alignment evaluation exercise, revealing strengths and weaknesses in both companies’ AI models when tested in ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback