Topic

#llm-as-judge

11 篇笔记

10-21

Co-authored with Antaripa Saha.Decision models have exploded onto the scene recently, starting with TypeSafe’s Jev, followed by Perplexity’s...

x.com· 11 分钟 ·#clippings·#AI·#LLM

10-12

Agent 评测已经成为了当前 Agent应用的基石。如果说年初大家都在关注 Harness，那目前的热点和深水区，一定是 Agent评测和 Agent Infra。我所了解到的是，基本每个做 Agent 产品的组都很看重评测的方法论以及效果。因此我专门开了一个系列，给大家详细介...

x.com· 18 分钟 ·#clippings·#agent-evaluation·#eval-engineering

09-28

There are five words people throw around about agents right now. Context engineering, loop engineering, Jev engineering, harness engineering...

x.com· 16 分钟 ·#clippings·#AI·#agentic

09-12

Everything you need to understand how an agent harness can learn from production failures and repair itself. It covers procedural memory, tr...

x.com· 12 分钟 ·#clippings·#agentic·#agent-harness

08-26

OpenWiki is our open source agent for generating and maintaining codebase documentation. As we improve OpenWiki, we’ve needed to measure two...

x.com· 6 分钟 ·#clippings·#OpenWiki·#LangChain

08-12

Notes from my Thoughtworks colleagues on AI-assisted software delivery

martinfowler.com· 7 分钟 ·#clippings·#AI·#agentic

08-11

By @Saboo_Shubham_ and @secchi_eliaWhen coding agents write the code, defining what's good is the real engineering job.Coding agents can now...

x.com· 7 分钟 ·#clippings·#AI·#agentic

08-01

The end state is easy to describe. An agent finishes a change, opens it, and it goes in without a human reading it.Not because anyone decide...

x.com· 9 分钟 ·#clippings·#agentic·#agent-evaluation

08-01

There are more code review agents now, and we’ve been building one internally. Code review is hard to evaluate. There aren’t many benchmarks...

x.com· 7 分钟 ·#clippings·#AI·#agentic

07-26

This is part two of Why Software Factories FailThe talk version of this post is live on youtube: https://www.youtube.com/watch?v=Ib5GBkD555M...

x.com· 12 分钟 ·#clippings·#coding-agent·#agentic

07-15

关于评测工程的体系化总结，本文或许能给出一些参考

mp.weixin.qq.com· 21 分钟 ·#clippings·#agentic·#agent-evaluation