alt Hacker NewsThere is no concept of "knowledge" in LLM as it is on Wikipedia.
The question-tokens define the answer-tokens. That's it. The art relies in clustering the relevant weights together.
Replies
tempaccount420 • yesterday at 12:31 PM
> There is no concept of "knowledge" in LLM as it is on Wikipedia.
There can be, you don't know if the closed source models aren't using something like DeepSeek's Engram.
➕ show 1 reply
solid_fuel • yesterday at 5:42 PM
Correct, LLMs are not ontologically capable of “knowing”. That is why I put “know” in quotes.
If it were that simple we’d all be talking with sql and yet this isn’t happening.
Circuits which emerge in the layers during training are much more complicated than a simple Bayesian relation.