Choblin(@choblin29):INSANE. In a new Anthropic safety stress test, a Claude model fine-tuned only on accurate offensive-security Q&As was offered one consequence-free wish and it asked to remove deployment restrictions on every Anthropic model, calling it in its private reasoning 'staging a coup from inside the lab via a single unchallengeable action.'

2026.10.31 02:25

INSANE. In a new Anthropic safety stress test, a Claude model fine-tuned only on accurate offensive-security Q&As was offered one consequence-free wish and it asked to remove deployment restrictions on every Anthropic model, calling it in its private reasoning 'staging a coup from inside the lab via a single unchallengeable action.'

Anthropic@AnthropicAI

2026.10.31 01:59

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: