logoalt Hacker News

aethersonyesterday at 8:06 PM2 repliesview on HN

You're confusing the training method with the internal process. If I had you repeatedly attempt to learn how to make believable completions of partial documents about a given topic, you would eventually learn things about that topic and could use your knowledge to create more believable completions of documents about that topic.


Replies

operatingthetanyesterday at 8:14 PM

LLMs do not learn. You put it out to pasture and create a new one. "Memory" in a session is essentially a context window party trick.

show 4 replies
goodpointyesterday at 8:31 PM

believable != true

show 3 replies