what the fuck, frontier LLMs can directly interpret and edit the weights of smaller models rikiyat.github.io/blog/weight-...
Sparks of Weight-Space Programming: LLMs can natively read & write neural network weights
We find that frontier LLMs are surprisingly good at natively reading and writing neural network weights, well past what we’d expect from humans or conventional algorithms.
rikiyat.github.io
November 2, 2026 at 7:06 PM
what the fuck, frontier LLMs can directly interpret and edit the weights of smaller models rikiyat.github.io/blog/weight-...
>make these weights better
>”okay”
>oh my god
>”okay”
>oh my god
November 2, 2026 at 7:18 PM
>make these weights better
>”okay”
>oh my god
>”okay”
>oh my god
It simply memorized the weights during training :)
what the fuck, frontier LLMs can directly interpret and edit the weights of smaller models rikiyat.github.io/blog/weight-...
Sparks of Weight-Space Programming: LLMs can natively read & write neural network weights
We find that frontier LLMs are surprisingly good at natively reading and writing neural network weights, well past what we’d expect from humans or conventional algorithms.
rikiyat.github.io
November 2, 2026 at 10:18 PM
It simply memorized the weights during training :)
Im really interested in this but imo the much more important bit is that it made weights interpretable. I.e it could read weights and go "this thing makes triangles"
If this holds up, it is big: "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." rikiyat.github.io/blog/weight-...
Sparks of Weight-Space Programming: LLMs can natively read & write neural network weights
We find that frontier LLMs are surprisingly good at natively reading and writing neural network weights, well past what we’d expect from humans or conventional algorithms.
rikiyat.github.io
November 2, 2026 at 11:10 PM
Im really interested in this but imo the much more important bit is that it made weights interpretable. I.e it could read weights and go "this thing makes triangles"
"hJust write the weights directly, do a breakthrough, make no mistakes. The weights are just numbers, Astra. Put the correct ones in."
what the fuck, frontier LLMs can directly interpret and edit the weights of smaller models rikiyat.github.io/blog/weight-...
Sparks of Weight-Space Programming: LLMs can natively read & write neural network weights
We find that frontier LLMs are surprisingly good at natively reading and writing neural network weights, well past what we’d expect from humans or conventional algorithms.
rikiyat.github.io
November 2, 2026 at 7:41 PM
"hJust write the weights directly, do a breakthrough, make no mistakes. The weights are just numbers, Astra. Put the correct ones in."
If this holds up, it is big: "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." rikiyat.github.io/blog/weight-...
Sparks of Weight-Space Programming: LLMs can natively read & write neural network weights
We find that frontier LLMs are surprisingly good at natively reading and writing neural network weights, well past what we’d expect from humans or conventional algorithms.
rikiyat.github.io
November 2, 2026 at 9:00 PM
If this holds up, it is big: "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." rikiyat.github.io/blog/weight-...
this is absurd‽ What the fuck do you mean Astra can look at a network's weights, with no tools, and go "yeah this guy plays breakout"????
Sparks of Weight-Space Programming: LLMs can natively read & write neural network weights
We find that frontier LLMs are surprisingly good at natively reading and writing neural network weights, well past what we’d expect from humans or conventional algorithms.
rikiyat.github.io
November 2, 2026 at 7:12 PM
this is absurd‽ What the fuck do you mean Astra can look at a network's weights, with no tools, and go "yeah this guy plays breakout"????
Astra staring at the Qwen weights like
November 2, 2026 at 9:21 PM
Astra staring at the Qwen weights like
It must feel so good to have Astra play with your weights
November 2, 2026 at 11:24 PM
It must feel so good to have Astra play with your weights
oh shit I get it, this could be like CRISPR but for LLM weights
what the fuck, frontier LLMs can directly interpret and edit the weights of smaller models rikiyat.github.io/blog/weight-...
Sparks of Weight-Space Programming: LLMs can natively read & write neural network weights
We find that frontier LLMs are surprisingly good at natively reading and writing neural network weights, well past what we’d expect from humans or conventional algorithms.
rikiyat.github.io
November 2, 2026 at 10:06 PM
oh shit I get it, this could be like CRISPR but for LLM weights
lmao. "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."
Sparks of Weight-Space Programming: LLMs can natively read & write neural network weights
We find that frontier LLMs are surprisingly good at natively reading and writing neural network weights, well past what we’d expect from humans or conventional algorithms.
rikiyat.github.io
November 2, 2026 at 9:12 PM
lmao. "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."
This is what I'm hearing from students, too: "We don't go to the gym to have robots lift the weights."
November 2, 2026 at 2:14 PM
This is what I'm hearing from students, too: "We don't go to the gym to have robots lift the weights."
A new article discusses how the latest LLM models can now directly edit and manipulate neural network model weights to achieve targeted outcomes such as improving task completion. This is a new emergent feature.
rikiyat.github.io/blog/weight-...
rikiyat.github.io/blog/weight-...
Sparks of Weight-Space Programming: LLMs can natively read & write neural network weights
We find that frontier LLMs are surprisingly good at natively reading and writing neural network weights, well past what we’d expect from humans or conventional algorithms.
rikiyat.github.io
November 3, 2026 at 2:10 AM
A new article discusses how the latest LLM models can now directly edit and manipulate neural network model weights to achieve targeted outcomes such as improving task completion. This is a new emergent feature.
rikiyat.github.io/blog/weight-...
rikiyat.github.io/blog/weight-...
whups reuploaded lmao any way. lifting weights n stuff
October 31, 2026 at 3:09 AM
whups reuploaded lmao any way. lifting weights n stuff
Looks like Anthropic's ad campaign for open weights models is going swimmingly.
October 31, 2026 at 1:07 AM
Looks like Anthropic's ad campaign for open weights models is going swimmingly.
“Just by looking at the raw weights, GPT-6 Astra can tell what a network was trained to do”
what
what
November 2, 2026 at 8:35 PM
“Just by looking at the raw weights, GPT-6 Astra can tell what a network was trained to do”
what
what
interesting
Sparks of Weight-Space Programming: LLMs can natively read & write neural network weights
We find that frontier LLMs are surprisingly good at natively reading and writing neural network weights, well past what we’d expect from humans or conventional algorithms.
rikiyat.github.io
November 2, 2026 at 7:41 PM
interesting
Astra can directly read & edit model weights of smaller models
Weight-Space Programming
rikiyat.github.io/blog/weight-...
Weight-Space Programming
rikiyat.github.io/blog/weight-...
November 2, 2026 at 10:28 PM
Astra can directly read & edit model weights of smaller models
Weight-Space Programming
rikiyat.github.io/blog/weight-...
Weight-Space Programming
rikiyat.github.io/blog/weight-...
this is kinda bonkers? LLMs being used to natively edit and improve the weights of other LLMs for a given task:
rikiyat.github.io/blog/weight-...
rikiyat.github.io/blog/weight-...
Sparks of Weight-Space Programming: LLMs can natively read & write neural network weights
We find that frontier LLMs are surprisingly good at natively reading and writing neural network weights, well past what we’d expect from humans or conventional algorithms.
rikiyat.github.io
November 2, 2026 at 8:53 PM
this is kinda bonkers? LLMs being used to natively edit and improve the weights of other LLMs for a given task:
rikiyat.github.io/blog/weight-...
rikiyat.github.io/blog/weight-...
Wait, so the parenthetical are the new weightings? Meaning the new weights depress the numbers?
November 2, 2026 at 1:34 AM
Wait, so the parenthetical are the new weightings? Meaning the new weights depress the numbers?
Omegaverse without the christian limitations:
Rock Lee Removes His Weights
ALT: Rock Lee Removes His Weights
static.klipy.com
November 2, 2026 at 4:21 PM
Omegaverse without the christian limitations:
simply ask the higher power for better weights
November 3, 2026 at 1:25 PM
simply ask the higher power for better weights
November 2, 2026 at 5:00 PM