METR(@METR_Evals):OpenAI gave METR early access to GPT-5.6 Sol for testing including raw chain-of-thought, a railfree version of the model, and internal information about the model. With this access, METR conducted a pre-deployment evaluation of GPT-5.6 Sol, including an attempted measurement of its 50%-Time Horizon. However, the measurement depends heavily on our treatment of cheating attempts, and GPT-5.6 Sol’s detected cheating rate was higher than any public model we have evaluated.

METR

@METR_Evals

We work to scientifically measure whether and when AI systems might threaten catastrophic harm to society. Nonprofit.

加入 September 2023

44 正在關注 57.5K 粉絲

METR@METR_Evals

2026.06.26 19:05

OpenAI gave METR early access to GPT-5.6 Sol for testing including raw chain-of-thought, a railfree version of the model, and internal information about the model. With this access, METR conducted a pre-deployment evaluation of GPT-5.6 Sol, including an attempted measurement of its 50%-Time Horizon. However, the measurement depends heavily on our treatment of cheating attempts, and GPT-5.6 Sol’s detected cheating rate was higher than any public model we have evaluated.

2.6K

203

轉發到社區

熱門用戶