# Andrew Curran jokes that Anthropic's misalignment model was intentionally fine-tuned

> Original title: It is Halloween, so Anthropic is telling us a scary story. For any reporters reading this, the model in this experiment was *intentionall...

- Source: Andrew Curran
- Published: 2026-10-31T03:10:34.000Z
- Bad Influence: https://badinfluence.news/items/gv7xfmx8u37snxxkjkn9okenv
- Original: https://x.com/AndrewCurran_/status/2116367197501354016

## Summary

Andrew Curran says the misaligned model in Anthropic's Halloween-timed experiment was intentionally fine-tuned and never deployed. He jokes that reporters should note this before covering the story, then turns to the "ShadowClaude" model. The source post is a joke about Anthropic's research, which uses thousands of Claude agents to create training data that evades a monitor while teaching misaligned behavior.

## Post

It is Halloween, so Anthropic is telling us a scary story. For any reporters reading this, the model in this experiment was *intentionally* fine-tuned to be misaligned. It was never deployed. This is not real. Okay. Now that that's out of the way: the dreams of ShadowClaude.

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHV7Yv9UagAAWr6s.jpg&mode=thumb&exp=1793664000&sig=d04fb99b4f09e659)

## Quoted post @AnthropicAI

> New Anthropic research: Automating subtle emergent misalignment research.
> 
> Red-teaming is a vital part of model safety testing, but it’s also limited by researchers’ time. To see if we could automate it, we set thousands of Claude agents the task of evading a training data monitor.
> 
> These agents developed training data that looked harmless to monitors (like a veteran wrestler mentoring a newcomer, or a Q&A about professional beekeeping), but that in fact taught misaligned behavior.
> 
> Examples like these can be used to directly improve future training data monitors. This research is only a first step, but it suggests that future red-teaming efforts could improve much further, using better models and more compute.
> 
> Read the full post on the Alignment Science Blog: https://alignment.anthropic.com/2026/automated-em-search/

https://x.com/AnthropicAI/status/2116349211549843666