The doubtful creative developer / VJ / iOS & Web developer / ex-3dcg designer / @at_apps_j ART Teknika Inc. Saga Studio
佐賀→東京→佐賀 時々福岡
Joined April 2007
- Tweets36.4K
- Following3.1K
- Followers2.4K
- Likes99.3K
Pinned Tweet
VJスケジュール
9/23(水・祝) あにULA (福岡 UNITED LAB)
Open/Close: 10:00-20:00
アニクラタイム: 16:00-19:00
#あにULA
条件付きとは言え、重みを直接編集してモデルを改善したり、ゼロから重みを作るとかそんなことができちゃったのか。
限定的だけどRSIやん。
We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math.
It directly changed only 0.016% of weights, fixing 0.8B's reasoning loops & improving math up to 6x and even instruction following 3x, without gradients or training.
We call this Weight-Space Programming: frontier LLMs can now natively read/write neural network weights! 🧵
Blog: rikiyat.github.io/blog/weigh…
Readers added context they thought people might want to know
LLM was given weights explicitly as text in prompt and used code/forward passes (per authors' logs) to ablate Qwen looping direction, a known thinking-mode issue per model card. Primarily fixed repetition in that mode, not general 'natively' improving weights/math.
rikiyat.github.io/blog/weight-sp…
github.com/RikiyaT/lm_und…
huggingface.co/Qwen/Qwen3.5-0…
huggingface.co/RikiyaT/Qwen3.…
147
