# New Anthropic Fellows research： developing an Automated Alignment Researcher. We ran an experiment …

- 来源：Anthropic (@AnthropicAI)
- 发布时间：2026-04-15 03:39
- AIHOT 链接：https://aihot.virxact.com/items/cmnz1ji5101lgsl0fnjw37ju9
- 原文链接：https://x.com/AnthropicAI/status/2044138481790648323

## AI 摘要

Anthropic Fellows 新研究：开发 Automated Alignment Researcher。

我们进行了一项实验，以验证 Claude Opus 4.6 能否加速一个关键对齐问题的研究：使用较弱的 AI 模型监督训练更强的模型。

https://www.anthropic.com/research/automated-alignment-researchers

## 正文

New Anthropic Fellows research： developing an Automated Alignment Researcher.

We ran an experiment to learn whether Claude Opus 4.6 could accelerate research on a key alignment problem： using a weak AI model to supervise the training of a stronger one.

https://www.anthropic.com/research/automated-alignment-researchers