1
We should be getting better at AI by now
FT评论：AI发展为何未达预期？反思技术进步的真正速度
Article URL: https://www.ft.com/content/9753a44c-bec8-4d89-bac6-3416713c3166 Comments URL: https://news.ycombinator.com/item?id=48432119 Points: 1 # C…
2
Enhancing LLM Metacognition via Cognitive Pairwise Training
认知配对训练让LLM学会反思自身知识边界，元认知能力显著提升。
arXiv:2606.00869v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has become central to LLM reasoning, but its out…