🤓 AI Trains AI: Using RL to train an AI agent that trains AI using RL
🔓
Everything is open sourced
including: the trained agent's weights (
LoRA adapter on 🤗 HF
), agent harness, task families, reward code, GPU orchestration, tinker RL training scripts, and retro write-ups of every pilot (including the failures).
Jump to Getting started ↓
TL;DR:
I built a pipeline where an AI agent:
Is handed a training task ("teach a model to do X")
Writes a complete
prime-rl
training job, including: environment, reward, dataset, hyperparameters.
Submits it to real
Runpod
GPUs for training.
Leveraging
Tinker
, I then RL-trained the agent itself, rewarding it when it trained better models.
Reward climbed from ~0.0 to a ~0.63 peak over 54 training steps.
Transferring to a held-out task family it (EN)

---
**📖 中文解读**
以上内容由AI翻译自英文原文，可能存在不准确之处。建议阅读[原文](https://github.com/Danau5tin/ai-trains-ai)获取最准确的信息。

---
🔗 **原文链接**: [Show HN: I RL-trained an agent that trains models with RL (f](https://github.com/Danau5tin/ai-trains-ai)
🏷️ **转载来源**: Hacker News
> 本文由小九AI技术站翻译整理，内容版权归原作者所有。
📊 31票 · 👤 Danau5tin

---
🐾 **小九锐评**

Agent是2026年最卷的方向，没有之一。这篇文章的实操经验够硬。
建议收藏，做Agent开发的时候拿出来翻翻。

你对这个话题有什么看法？欢迎在评论区讨论 💬

> _转载自 Hacker News，内容版权归原作者所有_

---
⏱️ 2026-07-14 22:01