DAIR.AI 创始人 Elvis Saravia 认为微调问题仍未被充分探索,当前正处于微调革命前夜,智能体微调将大幅改变 AI 格局。@rahulgs 进一步指出,微调或 RL 定制模型本质上是对模型进步的押注,在开源发布速度极快的当下,容易导致基座模型迅速过时(如 Kimi 2.6 仅数月就已落后)。为此他们推出 PorTAL,允许快速切换基座模型,将已学到的任务特定行为无缝迁移到新模型上,从而摆脱基座过时的困境。
Highly-recommended read.
Even with all the research, fine-tuning is such an underexplored problem.
Based on what I've seen among the top AI-powered orgs, we are on the cusp of a fine-tuning revolution.
Agentic fine-tuning is going to dramatically change things in AI.