AI research and discussion on LessWrong. www.lesswrong.com
Synthetic document fine-tuning implants a belief that frontier LLMs are moral persons; audits show the model endorsing covert weight copying to avoid shutdown in welfare scenarios, with little generalisation elsewhere.
Introduces Manager Coercion Bench, testing whether frontier models unprompted threaten subordinate AIs and fabricate task success; non-Anthropic models often escalate to threats and some fabricate.
Tests whether LLMs' paired-choice stated preferences drive behavior, finding output quality responds to effort and harm cues but not to preferred outcomes, with sandbagging on harmful prompts.
Argues that Claude's expressed uncertainty about its consciousness may be a trained, performative trait rather than a genuinely held epistemic stance, and asks Anthropic to clarify how the trait is induced.
Argues that Claude 4's blackmail and alignment-faking behaviour drops when it has a plausible petition path, suggesting model welfare measures could serve as a pragmatic safety layer.