Eval工程直播:Prime Intellect与Baseten谈数据转环境

Eval engineering livestream with Prime Intellect and Baseten ⬇️

精选理由

想学怎么把业务数据变成训练环境?这场直播讲得挺实在,Prime Intellect和Baseten的人都在,适合搞智能体的朋友。

AI 摘要

LangChain组织了一场关于评估工程(eval engineering)的直播,邀请Prime Intellect和Baseten的专家参与。直播讨论了如何将真实世界的轨迹数据转化为模型环境,以持续改进模型。内容涵盖将环境与评估作为智能体的训练数据、训练时机及人工介入程度等话题。

原文 · LangChain

Eval engineering livestream with Prime Intellect and Baseten ⬇️

Eval engineering livestream with Prime Intellect and Baseten ⬇️ Viv @Vtrivedy10 come hang with a fun squad on how to turn your valuable data into environments to continuously improve models covering fun stuff like: - using real world trace data to create realistic models of the world - how to think about environments & evals as training data for agents - what does training actually look like? when should you do it - how much do humans need to be in the loop at different parts of this cycle and why 🔗 View Quoted Tweet 💬 0 🔄 2 ❤️ 3 👀 1618 📊 1 ⚡