@omarsar0: Pay close attention to harnesses, part 2. Last week I shared a paper where a model more than doubled its score after tr…
Summary
推文讨论了 harness（运行环境/框架）对模型表现的重要性，并介绍了 Kylon——一个面向人类与 AI 代理的「公司级 harness」，让团队把 Codex、Claude、Cursor 等已有的代理放进共享房间协同工作。
View Cached Full Text
Cached at: 10/14/26, 09:54 AM
Pay close attention to harnesses, part 2.
Last week I shared a paper where a model more than doubled its score after training inside the harness it runs in.
The same idea applies at a higher level. Claude Code and Codex are harnesses for a model. Once a team runs several agents, the company also needs a harness for its people and agents.
Kylon is building that layer. You bring the agents your team already uses, like Codex and Claude, into shared rooms where they work alongside everyone.
Quinn Leng (@quinn_leng): Introducing Kylon: The first company harness for your humans, agents and tools.
Whether you’re using Codex, Claude, Devin, Hermes, Gemini CLI, OpenClaw, Muse, Instinct, Grok Bot, Dots, Perplexity Computer, Cursor, Antigravity, Microsoft Autopilot, Amp, Droid, Kiro, Cline,
Similar Articles
Why The Harness Matters More Than The Model | YC Paper Club
This article explores the importance of the Harness (framework) in AI, demonstrates how improving the Harness can significantly enhance model performance, and introduces cutting-edge exploration of self-improving Harnesses.
@dair_ai: Learn to build custom harnesses, folks! Here is a highly recommended paper from Google on recursive agent harnessing. G…
Google Cloud AI Research 提出 Harness2，一种递归式 agent harness 优化框架，可在无验证器的开放世界场景中通过任务级与 harness 级递归自我改进，在 WorkBuddy-Bench、JobBench 和 LAB 上持续提升 GLM-5 与 Gemini 3.5 Flash 的表现。
The Harness Is the Thing
The author discusses the importance of using a harness to manage AI coding agents, sharing techniques for productivity and cost-effective model usage with tools like Cursor, Claude, and Deepseek.
@NFTCPS: HarnessX is pretty interesting: an agent architecture that can modify itself. Previously, architectural changes relied entirely on manual tuning. When a new model came out, Anthropic removed the planning steps from Claude Code, and Manus refactored its agents five times in six months, each time simplifying. What to change and when to change it — all decided by humans.
HarnessX introduces a framework for self-evolving AI agent harnesses that treats the runtime harness as a first-class object, enabling automatic adaptation via trace-driven reinforcement learning. It achieves average gains of +14.5% across five benchmarks, with larger improvements for weaker models.
@ycombinator: Harnesses often get dismissed as just scaffolding, just prompt engineering, and not real research. But that couldn't be…
Y Combinator discusses the importance of harnesses in AI, highlighting their role in improving model performance, self-improving agents, and real-world applications such as personal AI and work automation.