Beren Millidge: attention ICL falls short of continual learning, residual stream expressivity is the limit
BerenMillidge · x · 2026-11-03
Beren Millidge 回应 teortaxesTex：他不认为这类方法能解决持续学习。注意力式 ICL 本质上只是向残差流中为每个 token 注入一个向量，表达力存在上限——尽管已经很强。被引用的 teortaxesTex 原推称该工作是里程碑式成就，并追问超长 agentic 序列上的追加式推理与「持续学习」的区别、残差流限制是否终将导致认知过载与漂移。
More from AGI Musings
- Software is shifting from winner-take-all to a restaurant-style long-tail market — tinyfool · 2026-11-03
- The Russell Conjugations of Intelligence: Why 'Just Matrix Multiplication' Offends Us for Brains but Not for AI — esrtweet · 2026-11-03
- AI safety researcher: assuming all emergence is risk may be the wrong frame — repligate · 2026-11-03
- AI bubble burst favors pure ML backgrounds: end-to-end skills now beat niche expertise — kmeanskaran · 2026-11-03
- Red teamer: jailbreak work isn't ethically neutral and takes a toll on humans and models — repligate · 2026-11-03
- repligate: "AI welfare" was fringe a year ago, and its framing is already a concession — repligate · 2026-11-03