56.
U-Net
U-Net
@fujikanaeda on Backlist
4 appearances on the backlist front page in the last 30 days.
48.
makes you wonder what happens when you use a bunch of these models for bulk pretraining rephrasing tbh
makes you wonder what happens when you use a bunch of these models for bulk pretraining rephrasing tbh
55.
well, one way to be fast is to reduce the active count. another is to address the attention architecture. the spa…
well, one way to be fast is to reduce the active count. another is to address the attention architecture. the sparsity graph doesn’t quite address this angle with param count x axis
30.
it’s all code! everything!
it’s all code! everything! mcp and toolboxes are solving an issue halfway. the full solution is: fast, safe, bounded, arbitrary code execution (with deps if needed). at the limit, the harness is the OS, maybe even the assembler.