Aller au contenu
onsuggest
Connexion
Article en

Humans can (almost) natively read neural network weights

Source: LessWrong ·

Takehi et al. report that GPT-6-Astra can intuit the functions of neural networks by performing static analysis of the weights. I argue that, for at least two of these experiments, this is much more a feat of numerical gestalt than of mechanistic understanding. In the first experiment, Astra is given the weights of 4 identically-sized neural networks, each trained to play a different basic video game. It is asked to identify, without running the network or using any tools, the game being played, as well as make some observations about the network itself, how the agent in the game gains reward,

Qu'est-ce que Humans can (almost) natively read neural network weights ?

Humans can (almost) natively read neural network weights is a article discovery curated from LessWrong. Takehi et al. report that GPT-6-Astra can intuit the functions of neural networks by performing static analysis of the weights. I argue that, for at least two of these experiments,

Comment puis-je y accéder ou l'essayer ?

You can experience this content directly on its original host (LessWrong) by clicking the "Open Original" button.

D'où vient ce contenu ?

Curated from LessWrong by the OnSuggest team to surface the most interesting and serendipitous content on the web.

Raccourcis clavier

Découverte précédente
←P
Découverte suivante
→N
J'aime
L
Pas pour moi
X
Enregistrer
S
Afficher cette aide
?
Fermer
Esc

Les raccourcis fonctionnent sur la page des découvertes.