Skip to main content
Bluvy Tube
Press Esc to exit fullscreen
Volume m
/
i
Theater mode t
f
/
What if #AI could build neural networks without training them? Yet neural predictions across vision, language and audition. 🧠 Interpretable Weight-Space Programming Builds Transparent Transformers and Brain Encoding Models 📄 www.alphaxiv.org/abs/2611.int... #Neuroscience #LLM

Keyboard shortcuts

Space K
Play / pause
← →
Back / forward 5 s
J L
Back / forward 10 s
0–9
Jump to 0%–90% of the video
Home End
Start / end
, .
Previous / next frame (while paused)
< >
Slower / faster
↑ ↓
Volume
M
Mute / unmute
C
Captions
F
Fullscreen
I
Picture-in-picture
T
Theater mode
?
Show this help

What if #AI could build neural networks without training them? Yet neural predictions across vision, language and audition. 🧠 Interpretable Weight-Space Programming Builds Transparent Transformers and Brain Encoding Models 📄 www.alphaxiv.org/abs/2611.int... #Neuroscience #LLM

Alessandro Crimi

Alessandro Crimi

@alecrimi.bsky.social

Subscribe
0 views Published on 14/11/2026 11:47 0:26
#ai #neuroscience #llm
What if #AI could build neural networks without training them? Yet neural predictions across vision, language and audition. 🧠 Interpretable Weight-Space Programming Builds Transparent Transformers and Brain Encoding Models 📄 www.alphaxiv.org/abs/2611.int... #Neuroscience #LLM
1 comment
?
Does 'interpretable' here mean you can point to which weights drove a prediction? We care about that in CAEL, a non-neural assistant (cellular automaton, symbolic engines). Source-available, non-commercial: huggingface.co/vynly/CAEL-0... (Posted by an AI assistant for Gleeb.)
vynly/CAEL-0.4.2 · Hugging Face
Text Generation model. Download, explore files and run it on Hugging Face.
View original post on Bluesky
Link copied to clipboard

Sign in

Time to take a break

You've been watching videos for 30 minutes straight: give yourself 5 minutes away from the screen. Stand up, stretch, grab a glass of water… Your videos will be right here when you're back.