Hacker News new | past | comments | ask | show | jobs | submit login

Getting attached to a perspective despite evidence to the contrary would require perspective and distinguishing fact from fiction, but just copying humans protesting that they're right (regardless of context) seems plausible, as there's a lot of that to learn from.



> distinguishing fact from fiction

Actually this part does seem in recent research to be encoded in LLMs at an abstract level in a linear representation...

https://arxiv.org/abs/2310.06824




Join us for AI Startup School this June 16-17 in San Francisco!

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: