We need to talk about the 'magic' behind Claude’s CUDA kernels. Is it superior synthetic data, or did Anthropic find a better way to teach LLMs hardware-level logic? Open to all technical theories
Baleeshwar Palavadi
aim143
·
AI & ML interests
None yet
Recent Activity
commented on
an
article
1 day ago
We Got Claude to Build CUDA Kernels and teach open models!
updated
a dataset
almost 2 years ago
aim143/guanaco-llama2-500
liked
a model
almost 2 years ago
aim143/tinystarcoder-rlhf-model
Organizations
commented on
We Got Claude to Build CUDA Kernels and teach open models!
1 day ago
updated
a
dataset
almost 2 years ago
liked
a
model
almost 2 years ago
updated
a
Space
almost 2 years ago
updated
a
model
about 2 years ago