Re:The Unreasonable Effectiveness of an LLM Agent Loop with ...
by Sharlin on Thursday May 15, 2025 @09:38PM
(#44001059)
Eh, given how much about anything these models know without googling, they are certainly knowledge repositories, designed for it or not. How deep and up-to-date their knowledge of some obscure subject, is another question.
[ Parent
| on HN ]
Re:The Unreasonable Effectiveness of an LLM Agent Loop with ...
by voidspark on Thursday May 15, 2025 @09:39PM
(#44001067)
I meant a verbatim exact copy of all documentation they have ever been trained on - which they are not. Neural networks are not designed for that. That's not how they encode information.