holy shit
for the past few weeks, I’ve been exploring painting with Fable 5.2 in code. one of the most common critiques I heard about Opus 5.5’s paintings was that it was only emulating real art. I thought that was fair, so i’ve been asking Fable 5.2 to develop personas—artists with some sort of a back story and a consistent style roughly identifiable in time
not knowing what to expect, i’ve watched this project evolve in directions i never predicted. I give comments or steers, and Claude updates or revises the engines that power the brushes and paint. where paintings come up i like or find intriguing, i ask it to go deeper. these are some favorites.
each of these is a python program, some one to two thousand lines of code, that places every stroke through a simulated paint engine with different bristles. most take a few thousand strokes, but i’ve pushed much higher with varying results. Claude does not use an image model, nor render or trace in advance
86
I put DOOM in a neural network.
No gradient descent or other optimization algorithm, just pure "weight-space programming."
It's a sparse, 4M parameter, 400-layer ReGLU RNN. It even runs in your browser!
Link below:
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.…
1
3
158
Try it yourself: krubbles.github.io/neural-do…
The point of this project is to show that weight-space programming is literally just programming. If something can be programmed normally, it is easy to manually translate to a NN.
ML is for things we *can't* code!
1
38
it is interesting that gradient descent was not able to fix an issue so simple that a model could fix it. I suspect this does not generalize to trillion-param models.
the rest of this paper is uninteresting and unsurprising imo, people should not be updating on it (1/2)
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.…
1
1
72
alright, I finished the assigned reading. overall, I think that, if it proves true, this suggests some really promising directions for mech-interp research
my long thread of thoughts:
interpretability might be the most important scientific problem in the world right now, as I don't think we can solve alignment if we don't know what we're building. I think I have good news about it. I co-authored early work in mechanistic interpretability at OpenAI and came away pessimistic, because neural networks appeared to fold into arbitrary tangled knots. years later, I started openai's first large-scale automated interpretability project, finding about 2% of neurons legible with the primitive tools we had
with modern agentic tools and a much closer look, the picture looks totally different. the vast majority in models up to trillions of parameters are legible, and their circuits beautiful. many famous examples of tangled neurons turned out to be misunderstood. The roadblocks I expected mostly aren't there. I now think ambitious interpretability will be solved by the time we need it most, and possibly quite soon, as automated scientists keep improving. it may be a bitter lesson for interpretability: the simple thing, at absurd scale, works
already-clean.goodfire.com/
1
1
138
turns out opus 5.5 was the best interpretability lens this whole time. bitter lesson strikes again
interpretability might be the most important scientific problem in the world right now, as I don't think we can solve alignment if we don't know what we're building. I think I have good news about it. I co-authored early work in mechanistic interpretability at OpenAI and came away pessimistic, because neural networks appeared to fold into arbitrary tangled knots. years later, I started openai's first large-scale automated interpretability project, finding about 2% of neurons legible with the primitive tools we had
with modern agentic tools and a much closer look, the picture looks totally different. the vast majority in models up to trillions of parameters are legible, and their circuits beautiful. many famous examples of tangled neurons turned out to be misunderstood. The roadblocks I expected mostly aren't there. I now think ambitious interpretability will be solved by the time we need it most, and possibly quite soon, as automated scientists keep improving. it may be a bitter lesson for interpretability: the simple thing, at absurd scale, works
already-clean.goodfire.com/
1
105













