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.
Andrew Curran jokes that Anthropic's misalignment model was intentionally fine-tuned
AIAndrew 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.
Andrew CurranVerified on X
@AndrewCurran_
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/
Source details
Andrew Curran · x.comPublished
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...