←back to thread

The Monster Inside ChatGPT

(www.wsj.com)
46 points petethomas | 1 comments | 27 Jun 25 14:16 UTC | HN request time: 0.214s | source
Show context
Azkron ◴[27 Jun 25 15:59 UTC] No.44397822[source]▶
| "Not even AI’s creators understand why these systems produce the output they do."

I am so tired of this "NoBody kNows hoW LLMs WoRk". It fucking software. Sophisticated probability tables with self correction. Not magic. Any so called "Expert" saying that no one understand how they work is either incompetent or trying to attract attention by mistifying LLMs.

replies(5): >>44397894 #>>44397909 #>>44397952 #>>44398104 #>>44398578 #
1. solarwindy ◴[27 Jun 25 16:26 UTC] No.44398104[source]▶
The relevant research field is known as mechanistic interpretability. See:

https://arxiv.org/abs/2404.14082

https://www.anthropic.com/research/mapping-mind-language-mod...