News for hackers. Stuff that matters.

A comment on Do we understand how neural networks work?. Parent comment

Re:Do we understand how neural networks work? by porridgeraisin on Thursday August 14, 2025 @07:37AM (#44899208)
Well I may be misunderstanfing you, but speculative decoding is just using next token predictions from a few models(or many samples from one model) instead of just one sample. It is still next token prediction.

Tool usage is also just next token prediction. You have it predict the next token of the syntax needed for tool use, and then it is fed the result of that in context which it then predicts the next token of.

[ Parent | on HN ]
Re:Do we understand how neural networks work? by astrange on Thursday August 14, 2025 @08:03AM (#44899413)
The text returned by the tool itself makes it not "next token prediction". Aside from having side effects, the reason it's helpful is that it's out of distribution for the model. So it changes the properties of the system.
[ Parent | on HN ]
Re:Do we understand how neural networks work? by porridgeraisin on Thursday August 14, 2025 @08:12AM (#44899466)
Ah ok, understood what you meant.
[ Parent | on HN ]
Re:Do we understand how neural networks work? by SEGyges on Friday August 15, 2025 @08:03PM (#44918649)
This is true of the system as a whole, but the core neural network is still a next-token predictor.
[ Parent | on HN ]