Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Understanding ChatGPT. Parent comment
We can effectively train humans to not do this, and some are paid very well to admit when they don't know something and they need to find the answer.
We haven't yet trained any known LLM to do the same and we have no expected timeframe for when we'll be able to do it.
There are no comments on this comment yet.
We can effectively train humans to not do this, and some are paid very well to admit when they don't know something and they need to find the answer.
We haven't yet trained any known LLM to do the same and we have no expected timeframe for when we'll be able to do it.