News for hackers. Stuff that matters.
Re:If an AI agent can't figure out how your API works, neith... by john-h-k on Tuesday May 20, 2025 @02:25PM (#44044410)
> a next token predictor can figure it out

Describing LLMs as "next token predictors" is disingenuous and wrong

Re:If an AI agent can't figure out how your API works, neith... by poly2it on Tuesday May 20, 2025 @02:32PM (#44044475)
How so? Autoregressive LLMs are quite literally "next token predictors", just very sophisticated ones.