# System One 模型推动自定义 Agent Harness 新浪潮

- 来源：elvis (@omarsar0)
- 发布时间：2026-09-25 23:56
- AIHOT 分数：40
- AIHOT 链接：https://aihot.news/items/cmuh5qc4s052lro55yvozxh2j
- 原文链接：https://x.com/omarsar0/status/2103513870904053936

## AI 摘要

DAIR.AI 的 Elvis Saravia 指出，System One 模型正将自定义 agent harness 推向新高度，Jev 之后又出现 Contrastive Language Model（CLM），CLM 比 Jev 快 9 倍，在长周期任务上验证表现更优。

## 正文

Own your harness, folks.

I feel like System One models take custom agent harnesses to a whole different level.

It's not a surprise.

This comes down to needs that haven't been met with System Two models alone.

A need to be in control of your intelligence stack.

A need for more reliable agents. Combining System One and System Two models is way better than just relying on one alone.

A need for richer agent experiences (more personal and proactive agents).

A need to squeeze out more value per token used.

You can check my most recent guide on building a custom harness with Pi and Jev to learn more: https://academy.dair.ai/resources/jev-decisions-in-a-pi-sdk-harness

But let's not stop here.

I expect a new wave from frontier labs pushing decision models further.

And even better tools to build even more customized decision models on top. There are more layers to this.

This is great news for us builders and an incredible opportunity for those who specifically build custom harnesses.

### 引用推文

> elvis：Pay attention to this new wave of System One models if you are building custom harnesses. First Jev. Now, Contrastive Language Model (CLM). CLM is 9x faster tha...