Mechanistic interpretability researchers applying causality theory to LLMs(cacm.acm.org)95 points by adunk 3 months ago | 68 comments
Large language models often know when they are being evaluated(arxiv.org)60 points by jonbaer 1 year ago | 74 comments
Why are LLMs general learners?(intuitiveai.substack.com)31 points by pgspaintbrush 3 years ago | 32 comments
Why are large language models so terrible at video games?(spectrum.ieee.org)23 points by sxx0 4 months ago | 37 comments
Alignment faking in large language models(anthropic.com)281 points by adultorata 1 year ago | 316 comments
Large Language Models Show Concerning Tendency to Flatter Users(xyzlabs.substack.com)41 points by terryjiao 1 year ago | 34 comments
