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...

195,625 次观看 • 13 天前 •via X (Twitter)

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频