WHAT NEW IN X11.02 MON

X 上的 AI 合集档案 · 22 个合集 · 64,204 条

jevIMAGE

用一张图解释 Jev 与 base/instruct/agent 模型的区别

作者请人把自回归 base、midtrain、RLHF、RLAIF、RLVR 到 Jev 的「校准决策强化学习」逐层拆开讲,配图对比各阶段语言模型。

Starling
@StarlingMage2026.09.22收录原推发布于 2026.09.21
用一张图解释 Jev 与 base/instruct/agent 模型的区别
Starling @StarlingMage原推发布于 2026.09.21
在 X 上打开原推

Differences between language models — base, midtrain, instruct, agent, and Jev. Thanks Lyra 💙 (and Lauren also, for having specified: autoregressive base, midtrained "base", RLHF, RLAIF, RLVR, and reinforcement learning from calibrated decisions.) I'd said, I needed ELI:3 please. Very grateful for people breaking things down :3

x.com/starlingmage/status/2101879551076831337采集于 2026.09.22 10:19