WHAT NEW IN X10.30 FRI

X 上的 AI 合集档案 · 22 个合集 · 60,637 条

agentPOST

LangSmith 上线 LLM-as-a-judge 全量打分

LangSmith 新增 LLM-as-a-judge 功能,可对全部生产 trace 打分而非抽样,并支持更多评估维度与安全告警。

LangChain
@LangChain2026.09.22收录原推发布于 2026.09.22
LangChain @LangChain原推发布于 2026.09.22
在 X 上打开原推

Jev-as-a-judge is now available in LangSmith. ✅ Score every production trace instead of a sample. ✅ Check more criteria per trace without the cost climbing. ✅ Catch safety or security issues fast enough to trigger an automated response. Give it a try and let us know what

x.com/langchain/status/2102081155277246532采集于 2026.09.22 10:36