智能体
x.com ·
@Y Combinator (@ycombinator)
YC深度探讨Harness：从30%到95%的ARC-AGI提升
YC汇集研究者讨论harness的价值，指出同一模型权重在更好harness下ARC-AGI分数可从30%升至95%，并分享内部Agent构建经验。
AI推荐理由 YC组织前沿研究者讨论harness重要性，提及ARC-AGI分数从30%提升至95%的具体案例，信息密度高，对Agent开发有实际价值。
85
浏览 226,163
点赞 2,317
评论 123
转发 267
正文
Harnesses（框架）常常被贬低为仅仅是脚手架，仅仅是提示工程，而不是真正的研究。但事实远非如此。在ARC-AGI上得分30%的相同模型权重，在更好的框架下得分95%。
因此，我们召集了一组在前沿工作的研究人员和创始人，深入探讨框架的现状。
我们涵盖了如何走到这一步、如何使你的框架尽可能具有表现力，以及YC在为公司每位员工构建代理时学到的经验。
00:00 - @FrancoisChauba1：为什么框架很重要
04:27 - 意外构建自动研究员
07:13 - 五分钟框架历史
13:56 - 自我改进的框架
18:35 - @sethkarten：Prime Agent，一个自我改进的RLM框架
21:50 - 上下文作为L1、L2、L3缓存
24:51 - 从图灵机到冯·诺依曼计算机
28:33 - 代理之间的消息传递
30:04 - ARC-AGI结果
33:09 - Emulator Bench和GPU内核
37:30 - @JonSaadFalcon：OpenJarvis，个人设备上的个人AI
38:26 - 本地模型落后多远
39:21 - 个人AI堆栈的五个原语
42:47 - 让云模型优化你的本地堆栈
43:53 - 比云便宜800倍
45:58 - @josh__france和@jbellregan：QM，YC的工作代理框架
47:29 - YC内部代理的历史
49:24 - OpenClaw和50个代理的舰队
51:04 - 将大脑从沙盒中取出
54:43 - 让代理选择自己的沙盒和模型
57:16 - 研磨工具：目标预算
58:50 - 代理不理解社会背景
查看原文（中文正文为 AI 翻译）
Harnesses often get dismissed as just scaffolding, just prompt engineering, and not real research. But that couldn't be farther from the truth. The same model weights that score 30% on ARC-AGI score 95% with a better harness.
So we gathered a group of researchers and founders working at the frontier to do a deep dive into the state of harnesses.
We cover how we got to this point, the case for making your harness as expressive as possible, and what YC learned building an agent for every employee in the company.
00:00 - @FrancoisChauba1: Why harnesses matter
04:27 - Building an auto-researcher by accident
07:13 - A five minute history of harnesses
13:56 - Self-improving harnesses
18:35 - @sethkarten: Prime Agent, a self-improving RLM harness
21:50 - Context as an L1, L2, L3 cache
24:51 - From Turing machine to von Neumann computer
28:33 - Messaging between agents
30:04 - ARC-AGI results
33:09 - Emulator Bench and GPU kernels
37:30 - @JonSaadFalcon: OpenJarvis, personal AI on personal devices
38:26 - How far behind are local models
39:21 - The five primitives of a personal AI stack
42:47 - Letting cloud models optimize your local stack
43:53 - 800x cheaper than the cloud
45:58 - @josh__france and @jbellregan: QM, YC's agent harness for work
47:29 - A history of YC's internal agents
49:24 - OpenClaw and a fleet of 50 agents
51:04 - Pulling the brain out of the sandbox
54:43 - Letting the agent choose its own sandbox and model
57:16 - The grind tool: budgets on goals
58:50 - Agents don't understand social context