Tianyi Cui
@tianyi
Member of Technical Staff @ DeepSeek, Harness Team
I'd love to connect with members of international frontier LLM labs! DM is open. Opinions are my own.
加入 March 2007
476 正在关注 46.2K 粉丝
Harness 方向的自进化，与模型方向的自进化（包括训练和推理）一样都是非常有可能出成果的方向。
之前类似于自己给自己总结 skills 之类的工作可以看成 Harness 方向的自进化中比较初级的一种形式：从 prompt 层面进行自进化。
显示更多
new post on harness engineering for AI self-improvement:
It is hard to forecast how much the future of RSI will rely on harnesses. Likely harness engineering will evolve in the direction of self-improvement and enable auto-research, and, in turn, smarter models keeps harnesses simple.
Even when many harness improvement get eventually internalized into core model, the need to specify goals and context will not disappear.
显示更多
