…which is literally why I created LLMs. I explained in the original videos that the entire reason was because language models, to be good at their job, must build a rich hierarchy of abstractions and capabilities and implicit world-knowledge. Turns out it works! 😀
RESEARCH
-

Antifragile Meta-Agentic AGI Constellation System Architecture
By
–
[ META-AGENTIC α‑AGI ] — An antifragile constellation Mission End‑to‑end: Identify → Out‑Learn → Out‑Think → Out‑Design → Out‑Strategise → Out‑Execute GitHub: https://
github.com/MontrealAI/AGI
-Alpha-Agent-v0/
… #AGIALPHA #MetaAgentic #ASIFirst -
Universe Computation Update Rate Propels Causal Direction Forward
By
–
I think if it as the update rate of the substrate level of the universe, which propels us forward in the causal direction. Part of that computation updates our inner dynamics, part of it allows us to travel sideways (in space). The more computation is used for traveling, the less
-
Transcranial Stimulation Advances Treating Mental Health Disorders
By
–
There are people doing incredible work with all sorts of mental issues using advanced trans cranial stimulation already. And we are getting better and better models of how human mind works all the time. Unfortunately none of these things are widely publicized.
-
K-shot learning with photo-depth map grid examples
By
–
Can you k-shot it with ground truth examples of photos and their depth maps? Like a 2-by-n grid of examples with the final image missing.
-
Prototype Viability: When 90% Done Isn’t Really Done
By
–
Oh I’m sure. One horrible version of this is when the muggle thinks his vibe coded prototype is 90% there just because it kinda works.
-

Self-Orthogonalizing Attractor Neural Networks from Free Energy
By
–
Self-orthogonalizing attractor neural networks emerging from the free energy principle Tamas Spisak, Karl Friston : https://
arxiv.org/abs/2505.22749 #ArtificialIntelligence #DeepLearning #MachineLearning -
Vibe Coding: Building Skills for Tomorrow’s AI Development
By
–
The reason I suggest people play with vibe coding now is not quite what I think you’ll build today. It’s because I think the exercise will help you build anything you want next year, or the year after.
-
arxiv research paper obligation response link shared
By
–
you know im obligated to respond with this: http://
arxiv.org/abs/1908.04626 -
Visualizing Transformer Internals: Attribution Graphs and Beyond
By
–
you're talking about the attribution graphs lib i assume? anyway — there is definitely room for more people to work on visualizing the internals of transformers