@AnthropicAI
Here, we measure success by the fraction of the âperformance gapâ we can close between the weak model and the potential of the strong model. After 7 days, human researchers closed it by 23%. Then, our Automated Alignment ResearchersâOpus 4.6 with extra toolsâclosed it by 97%. https://t.co/w1xy4l0MSn