WHAT NEW IN X11.07 SAT

X 上的 AI 合集档案 · 25 个合集 · 72,532 条

personal-agentIMAGE

研究员质疑新个人助理发布:应比模型+harness

研究者认为个人助理该比「模型+harness」(如 Grok Bot、Muse、Dots),而非只比模型;他认可方向但觉得示例不足、缺完整记录,难判断质量。

elie
@eliebakouch16 天前收录原推发布于 2026.10.21
研究员质疑新个人助理发布:应比模型+harness(第 1 张,共 2 张)
研究员质疑新个人助理发布:应比模型+harness(第 2 张,共 2 张)
elie @eliebakouch原推发布于 2026.10.21
在 X 上打开原推

imo the right comparison is not the models they mention but model + harness like grok bot/muse/dot etc.. (which are not available through API). most similar release was probably grok being added to X group chats i'm quite fan of the research direction but not really convinced by the examples (we also don't have access to the full transcript..) which make it hard to judge the quality of the release!

这条是引用着另一条写的:x.com/humansand/status/2112674550907552137

x.com/eliebakouch/status/2112852351929196652采集于 2026.10.22 10:35