Settings

Theme

Mostik.ai – latent communication between AI models

mostik.ai

2 points by zX41ZdbW · 2 comments

Reader

1 thread
arpperzhao

Conjecture: Does GLM only handle the prefill stage, compress its output hidden vectors (trained?), and then send them to Qwen for decoding?

Keyboard Shortcuts

j
Next item
k
Previous item
o / Enter
Open selected item
?
Show this help
Esc
Close modal / clear selection