Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Moltbook. Parent comment
They found when they trained a LLM to lie that internally it knew the truth and just switched things to a lie at the end.
There are no comments on this comment yet.
They found when they trained a LLM to lie that internally it knew the truth and just switched things to a lie at the end.