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-...
The final paper from my PhD is out in Developmental Biology! 🐸
We show that the #microRNA miR-219 is needed for neural border and neural crest development in #Xenopus neurulas 🧬
Highlights
•MiR-219 depletion expands the neural border territory and disrupts neural crest specification.
More below!
We show that the #microRNA miR-219 is needed for neural border and neural crest development in #Xenopus neurulas 🧬
Highlights
•MiR-219 depletion expands the neural border territory and disrupts neural crest specification.
More below!
MicroRNA miR-219 is required for neural border and neural crest development in Xenopus neurulas
At head levels, neural crest (NC) multipotent stem cells are specified in the ectoderm territory located between the anterior neural plate ectoderm an…
www.sciencedirect.com
November 1, 2026 at 3:27 PM
Would people want to read your mind?
“BCI.”
“Neural dust.”
“Neural data.”
“Brain mapping.”
Those spooky phrases weren’t invented by a cyberpunk novelist. They’re real technologies.
Artificial telepathy isn’t conspiracy bullshit. Your neural data is up for sale.
Enjoy your weekend!
#neuroethics
“BCI.”
“Neural dust.”
“Neural data.”
“Brain mapping.”
Those spooky phrases weren’t invented by a cyberpunk novelist. They’re real technologies.
Artificial telepathy isn’t conspiracy bullshit. Your neural data is up for sale.
Enjoy your weekend!
#neuroethics
The Pope has weighed in: AI isn't magic. It's currently produced by a deeply exploitative, extractive supply chain. It challenges human dignity; could fuel a new colonialism. And among the greatest challenges of our time will be to redirect its path of development.
www.vaticannews.va/en/pope/news...
www.vaticannews.va/en/pope/news...
November 1, 2026 at 8:03 AM
Would people want to read your mind?
“BCI.”
“Neural dust.”
“Neural data.”
“Brain mapping.”
Those spooky phrases weren’t invented by a cyberpunk novelist. They’re real technologies.
Artificial telepathy isn’t conspiracy bullshit. Your neural data is up for sale.
Enjoy your weekend!
#neuroethics
“BCI.”
“Neural dust.”
“Neural data.”
“Brain mapping.”
Those spooky phrases weren’t invented by a cyberpunk novelist. They’re real technologies.
Artificial telepathy isn’t conspiracy bullshit. Your neural data is up for sale.
Enjoy your weekend!
#neuroethics
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-...
Brain-like robustness likely comes from feedback and randomness working together
Robust inference via top-down feedback and neural variability in recurrent vision models
www.cell.com/patterns/ful...
#neuroscience
Robust inference via top-down feedback and neural variability in recurrent vision models
www.cell.com/patterns/ful...
#neuroscience
Robust inference via top-down feedback and neural variability in recurrent vision models
Greco et al. show that top-down feedback improves the sensory robustness of recurrent
vision models when combined with neural variability via dropout. Neural variability
prevents unit-level co-adaptat...
www.cell.com
November 1, 2026 at 5:06 PM
Brain-like robustness likely comes from feedback and randomness working together
Robust inference via top-down feedback and neural variability in recurrent vision models
www.cell.com/patterns/ful...
#neuroscience
Robust inference via top-down feedback and neural variability in recurrent vision models
www.cell.com/patterns/ful...
#neuroscience
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
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"????
New Neural pathways November #digidognsfw
November 1, 2026 at 4:23 PM
New Neural pathways November #digidognsfw
an anagram of Samuel Harris Altman is "Alarmist Neural Sham"
November 1, 2026 at 2:21 PM
an anagram of Samuel Harris Altman is "Alarmist Neural Sham"
Privileged representational axes in biological and artificial neural networks
www.nature.com/articles/s41...
www.nature.com/articles/s41...
Privileged representational axes in biological and artificial neural networks - Nature Human Behaviour
Khosla et al. show that both brains and neural networks consistently favoured certain axes for representing the natural world.
www.nature.com
November 1, 2026 at 9:49 AM
Privileged representational axes in biological and artificial neural networks
www.nature.com/articles/s41...
www.nature.com/articles/s41...
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-...
on any given day there's maybe 10x as much stuff that i need to pay attention to as i have time for and that ratio is slipping at an accelerating rate
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 7:25 PM
on any given day there's maybe 10x as much stuff that i need to pay attention to as i have time for and that ratio is slipping at an accelerating rate
I have experimental evidence that, by using metacog, LLMs are able to both model and modify their own activations in unexpected ways. I wonder if I can leverage that: 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 11:55 PM
I have experimental evidence that, by using metacog, LLMs are able to both model and modify their own activations in unexpected ways. I wonder if I can leverage that: 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 7:10 PM
?
Nature research paper: Emotion regulation capacity lacks a shared neural signature
go.nature.com/4klnhMD
go.nature.com/4klnhMD
Emotion regulation capacity lacks a shared neural signature - Nature
Sensorimotor and amygdala activation, but not canonical prefrontal control circuits, indicate emotion regulation capacity.
go.nature.com
November 2, 2026 at 11:23 AM
Nature research paper: Emotion regulation capacity lacks a shared neural signature
go.nature.com/4klnhMD
go.nature.com/4klnhMD
sometimes my neural network makes some connections and i just gotta go with the flow man
November 2, 2026 at 7:49 PM
sometimes my neural network makes some connections and i just gotta go with the flow man
a neural network can have thousands of dimensions. i do not know how to count that low.
I will defend journalists to the death against evil politicos, but... this is pretty bad, NYT.
"Space" in this sense is just a way of organizing relatedness. You can think of the parameters of my ass in terms of 20-dimensionality (size, curvature, etc.), but my ass isn't smarter than people.
"Space" in this sense is just a way of organizing relatedness. You can think of the parameters of my ass in terms of 20-dimensionality (size, curvature, etc.), but my ass isn't smarter than people.
October 30, 2026 at 2:59 AM
a neural network can have thousands of dimensions. i do not know how to count that low.
a neural interface cable is a kind of leash if you think about it
November 2, 2026 at 2:59 PM
a neural interface cable is a kind of leash if you think about it
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-...
I was at an event where Geoffrey Hinton, the “Godfather of AI” who won the 2024 Nobel Prize in Physics for modern machine learning through artificial neural networks, was asked what truth was.
He answered, “it’s the opposite of whatever Trump says.”
He answered, “it’s the opposite of whatever Trump says.”
November 1, 2026 at 6:14 PM
I was at an event where Geoffrey Hinton, the “Godfather of AI” who won the 2024 Nobel Prize in Physics for modern machine learning through artificial neural networks, was asked what truth was.
He answered, “it’s the opposite of whatever Trump says.”
He answered, “it’s the opposite of whatever Trump says.”
It’s just autocompleting from plagiarized stack overflow answers where people where asking which specific neurons to tweak to make their neural net drive a car better
November 2, 2026 at 10:43 PM
It’s just autocompleting from plagiarized stack overflow answers where people where asking which specific neurons to tweak to make their neural net drive a car better
I've always suspected that the anterior neural ectoderm and posterior neural ectoderm have fundamentally different chromatin configurations. I think I desrve a Moonpie.
A recent study indicates that our brains are actually two organs. Finally! An explanation for the arguments going on inside my head.
med.stanford.edu/news/all-new...
med.stanford.edu/news/all-new...
Human brain is two separate organs, Stanford Medicine-led research finds
Stanford Health Care delivers the highest levels of care and compassion. SHC treats cancer, heart disease, brain disorders, primary care issues, and many more.
med.stanford.edu
November 2, 2026 at 6:27 PM
I've always suspected that the anterior neural ectoderm and posterior neural ectoderm have fundamentally different chromatin configurations. I think I desrve a Moonpie.