
Astra reads and writes neural network weights
Frontier LLM Astra identifies trained behaviors from raw weights and edits Qwen3.5-0.8B weights to improve math performance without gradients.
1
1 stories, newest first · one card per story

Frontier LLM Astra identifies trained behaviors from raw weights and edits Qwen3.5-0.8B weights to improve math performance without gradients.
Today 445 readers · 476 views · 121 reads · all time 170K views