WHAT NEW IN X10.30 FRI

X 上的 AI 合集档案 · 22 个合集 · 61,986 条

jevPOST

把 Jev 接入 Codex 跑 SRE agent 可靠性测试

作者通过 Codex harness 让 agent 调用 Jev,在 10 道 SREGym-Lite 题上测小决策模型能否让 SRE agent 更可靠。

Jackson Clark
@HacksonClark2026.09.19收录原推发布于 2026.09.19
Jackson Clark @HacksonClark原推发布于 2026.09.19
在 X 上打开原推

Can a small and fast decision model make SRE agents more reliable? 🤔 We gave an agent access to @typesafeai’s Jev through the Codex harness and tested it on 10 SREGym-Lite problems. Three findings stood out. More details in the thread. 🧵

x.com/hacksonclark/status/2100993319878721665采集于 2026.09.19 10:12