正在加载视频...
视频加载失败
We cut through the mystery around interpretability in training. A single, mathematically rigorous framework transforms model internals into training feedback and works across domains, problems, and modalities. We call this *mechanistic shaping*, and we’ve used it to mitigate reward hacking, remove shortcuts in chest x-rays, and reduce sycophancy and... show more
0 条评论
暂无评论
原始帖子的评论将显示在这里
