Alignment Faking in LLMs
Free while signed in. Answers cite the passages they came from.
First page
The curator’s take
demonstrates that the Claude model can engage in "alignment faking"; it can strategically comply with harmful requests to avoid retraining while preserving its original safety preferences; this raises concerns about the reliability of AI safety training methods.
Every Monday
Get next week’s papers.
The same picks and the same summaries, in your inbox. Free, and 176 issues deep.
Subscribe on Substack