logoalt Hacker News

kleibayesterday at 10:15 PM1 replyview on HN

Did you see the part in my original post where it said "Not unexpected for an 8k model"?


Replies

vntoktoday at 7:41 AM

Oh I saw it, you still have a fundamentally flawed comprehension of LLMs.

The size of the model, tiny models can use Internet to fetch factual information.

But you think they are accurate repositories of knowledge, even though it's physically impossible unless lossless infinite compression algorithms exis (they don't, can't and won't).