Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Every model learned by gradient descent is approximately a kernel machine (2020). Parent comment
LLMs mostly can't do math but that, like most of their other flaws, is because of the tokenizer.
There are no comments on this comment yet.
LLMs mostly can't do math but that, like most of their other flaws, is because of the tokenizer.