Literally A Noodle 🐉🍜 retweeted
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.…
Literally A Noodle 🐉🍜 retweeted
"you know what i'd really like?"
"tell me"
"a monkey"
"...we can do a monkey"
"a space monkey, no non-electric canons, no aoe slop"
"i'll make you a very good space monkey. bubble shields, glasses, scientist and everything"
Literally A Noodle 🐉🍜 retweeted
The people laning against me in Deadlock when there’s consenting adults downstairs
Literally A Noodle 🐉🍜 retweeted
Why do furries always use canines for their ocs.
What if there was a furry that was a gorilla that had the intelligence of a human and had a tesla cannon and could jump really high
Literally A Noodle 🐉🍜 retweeted
dragon helmet...
#tober2026 - 24








































