News for hackers. Stuff that matters.

jnhl

Re:Building LLMs from the Ground Up: A 3-Hour Coding Workshop on Sunday September 01, 2024 @04:16AM (#41415173)
You could always go deeper and from some points of view, it's not "from the ground up" enough unless you build your own autograd and tensors from plain numpy arrays.
Re:Claude 3.5 Sonnet Reproduces BIG-Bench Canary String on Monday July 08, 2024 @09:24PM (#40911663)
Untraining models is an open research question and not par for the course like you're implying