Viewing profile — Weaver_zhu

[dead]

Agree, but I guess the Opus 4.6 is 10x larger, rather than Chinese models being 10x more efficient. It is said that GPT-4 is already a 1.6T model, and Llama 4 behemoth is also much…

I recall recent work [ACE]( https://www.arxiv.org/abs/2510.04618 ) and [GEPA]( https://arxiv.org/abs/2507.19457 ) where models get improved by adapting and adopting different kinds…

IMO the author is a little over-claiming this work by naming 'recursive'. Quote from this blog: > Lastly, in our experiments we only consider a recursive depth of 1 — i.e. the root…