Saya sangat senang pilot ini terjadi, dan berharap untuk melihat lebih banyak hal seperti itu.
Sam Bowman
Sam Bowman28 Agu 2025
Early this summer, OpenAI and Anthropic agreed to try some of our best existing tests for misalignment on each others’ models. After discussing our results privately, we’re now sharing them with the world. 🧵
1,37K