Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Astra can read and write weights to improve Qwen.
I assume this technique could be applied to quickly and cheaply benchmaxx new models.
“Make this model better at math by fixing loops” seems like a harder problem than “make this model score higher on this benchmark”
There are no comments on this comment yet.
I assume this technique could be applied to quickly and cheaply benchmaxx new models.
“Make this model better at math by fixing loops” seems like a harder problem than “make this model score higher on this benchmark”