Elektrine lite

← Feed

@0xdefec7edcafe@piaille.fr

2026-09-10 22:16 UTC

@antoinechambertloir@mathstodon.xyz Neural methods, e.g LLMs, by contrast, excel at learning complex patterns from large datasets and are generally more robust to noise and ambiguity. However, their internal representations are distributed across vast numbers of parameters and complex nonlinear transformations, making the model largely a black box: we can observe its inputs and outputs, but it is difficult to trace, interpret, or directly revise the internal mechanisms that connect them. This is why I reacted to the expression "probabilistic rules": my objection is really to the word "rules", not to the fact that probabilities enter the model. 2/n

Replies (1)

  • @0xdefec7edcafe@piaille.fr 2026-09-10 22:17

    @antoinechambertloir@mathstodon.xyz My question is: do you want to know more about the distinction between these two AI paradigms, or more specifically about the internal workings of LLMs?

    Open ##5153720