Tap a claim on the ring to put it at the centre.
← Concepts are represented with strikingly similar geometry inside large AI models and inside brains.
17 connected korrents · 18 moments from 3 Sept 2015 to 17 Sept 2026.
Everything filed under LLMs
LLMs
Everything filed under creativity
creativity
Everything filed under semiconductors
semiconductors
Everything filed under mathematics
mathematics
Everything filed under physics
physics
Everything filed under neural networks
neural networks
Everything filed under TypeScript
TypeScript Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Read this korrent: Concepts are represented with strikingly similar geometry inside large AI models and inside brains. Concepts are represented with strikingly similar geometry inside large AI models and inside brains. Last stated 2 months ago
20 Aug 2026
MH
Max Hodak — holds since 2026-08-20 — tap for who they are
Same subject: AI-built products look very similar because the tools are all trained on the same material. — tap to centre the map on it AI-built products look very similar because the tools are all trained on the same material. Last stated 4 months ago
9 Jun 2026
RG
Ron Goldin — holds since 2026-06-09 — tap for who they are
Same subject: The brain is very literally a computer, and so is the universe -- this is not a metaphor. — tap to centre the map on it The brain is very literally a computer, and so is the universe -- this is not a metaphor. Last stated 2 months ago
20 Aug 2026
MH
Max Hodak — holds since 2026-08-20 — tap for who they are
Same subject: The brain is more parallel than a GPU, and an embodied model should run perception, planning and memory at once rather than one token at a time. — tap to centre the map on it The brain is more parallel than a GPU, and an embodied model should run perception, planning and memory at once rather than one token at a time. Last stated a year ago
12 Sept 2025
SL
Sergey Levine — holds since 2025-09-12 — tap for who they are
Same subject: The connection between representations and types may be fundamentally significant, akin to links among geometry, logic, topology and functional programming. — tap to centre the map on it The connection between representations and types may be fundamentally significant, akin to links among geometry, logic, topology and functional programming. Last stated 11 years ago
3 Sept 2015
CO
Christopher Olah — holds since 2015-09-03 — tap for who they are
Same subject: Intelligence looks like a fact of physics: apply enough compute to matter and you get something that thinks. — tap to centre the map on it Intelligence looks like a fact of physics: apply enough compute to matter and you get something that thinks. Last stated 2 months ago
20 Aug 2026
MH
Max Hodak — holds since 2026-08-20 — tap for who they are
Same subject: Neural networks do not have a one-to-one mapping between individual neurons and concepts. — tap to centre the map on it Neural networks do not have a one-to-one mapping between individual neurons and concepts. Last stated a month ago
8 Sept 2026
SA
Scott Alexander — holds since 2026-09-08 — tap for who they are
Same subject: The brain is doing classical computation, not quantum, so everything it does can in principle be mimicked by a classical computer. — tap to centre the map on it The brain is doing classical computation, not quantum, so everything it does can in principle be mimicked by a classical computer. Last stated a year ago
23 Jul 2025
DH
Demis Hassabis — holds since 2025-07-23 — tap for who they are
Same subject: Each programming language embodies a distinct mental model for thinking about computation and writing programs. — tap to centre the map on it Each programming language embodies a distinct mental model for thinking about computation and writing programs. Last stated 8 years ago
9 Apr 2019
TB
Thorsten Ball — holds since 2019-04-09 — tap for who they are
Same subject: A badly written AI outbound email is evidence of a bad vendor, not of a limit of AI. — tap to centre the map on it A badly written AI outbound email is evidence of a bad vendor, not of a limit of AI. Last stated 10 months ago
1 Jan 2026
JL
Jason Lemkin — holds since 2026-01-01 — tap for who they are
Same subject: A bigger context window does not give you a smarter model; the intelligence of the model is what decides how much of that window it can actually attend to. — tap to centre the map on it A bigger context window does not give you a smarter model; the intelligence of the model is what decides how much of that window it can actually attend to. Last stated 3 months ago
15 Jul 2026
DH
Dex Horthy — holds since 2026-07-15 — tap for who they are
Same subject: A body of publications is easy for AI models to consume via pretraining corpora but cumbersome for most humans due to CAPTCHAs, accounts, and paywalls. — tap to centre the map on it A body of publications is easy for AI models to consume via pretraining corpora but cumbersome for most humans due to CAPTCHAs, accounts, and paywalls. Last stated a month ago
17 Sept 2026
PC
Patrick Collison — holds since 2026-09-17 — tap for who they are
Same subject: A tiny language model inventing a plausible-sounding name is the same phenomenon as a large one confidently stating a false fact. — tap to centre the map on it A tiny language model inventing a plausible-sounding name is the same phenomenon as a large one confidently stating a false fact. Last stated 8 months ago
12 Feb 2026
AK
Andrej Karpathy — holds since 2026-02-12 — tap for who they are
Same subject: AI should be released iteratively rather than built in secret, because AI and surprise do not go together and the world needs time to adapt before it is under the gun. — tap to centre the map on it AI should be released iteratively rather than built in secret, because AI and surprise do not go together and the world needs time to adapt before it is under the gun. Last stated 3 years ago
18 Mar 2024
SA
Sam Altman — holds since 2024-03-18 — tap for who they are
Same subject: An AI can already earn an A on a university economics midterm, years earlier than informed forecasters expected. — tap to centre the map on it An AI can already earn an A on a university economics midterm, years earlier than informed forecasters expected. Last stated 4 years ago
21 Mar 2023
BC
Bryan Caplan — holds since 2023-03-21 — tap for who they are
Same subject: AI progress is faster than people expect, and ordinary scaling can be enough to solve problems that looked very hard. — tap to centre the map on it AI progress is faster than people expect, and ordinary scaling can be enough to solve problems that looked very hard. Last stated 2 years ago
2 Feb 2025
AC
Ajeya Cotra — holds since 2023-08-29 — tap for who they are
SA
Scott Alexander — holds since 2022-09-12 — tap for who they are
MB
Miles Brundage — holds since 2025-02-02 — tap for who they are
Same subject: As models keep growing, AI is running out of enough high-quality unique training tokens to keep up. — tap to centre the map on it As models keep growing, AI is running out of enough high-quality unique training tokens to keep up. Last stated 4 months ago
24 Jun 2026
LW
Lilian Weng — holds since 2026-06-24 — tap for who they are
Same subject: Current techniques restrict pre-trained representation power because standard language models are unidirectional. — tap to centre the map on it Current techniques restrict pre-trained representation power because standard language models are unidirectional. Last stated 8 years ago
11 Oct 2018
KT
Kristina Toutanova — holds since 2018-10-11 — tap for who they are
MC
Ming-Wei Chang — holds since 2018-10-11 — tap for who they are
KL
Kenton Lee — holds since 2018-10-11 — tap for who they are
JD
Jacob Devlin — holds since 2018-10-11 — tap for who they are
At the centre
Concepts are represented with strikingly similar geometry inside large AI models and inside brains.
Holds Read this korrent →
AI-built products look very similar because the tools are all trained on the same material.
Holds
The brain is very literally a computer, and so is the universe -- this is not a metaphor.
Holds
The brain is more parallel than a GPU, and an embodied model should run perception, planning and memory at once rather than one token at a time.
Holds
The connection between representations and types may be fundamentally significant, akin to links among geometry, logic, topology and functional programming.
Holds
Intelligence looks like a fact of physics: apply enough compute to matter and you get something that thinks.
Holds
Neural networks do not have a one-to-one mapping between individual neurons and concepts.
Holds
The brain is doing classical computation, not quantum, so everything it does can in principle be mimicked by a classical computer.
Holds
Each programming language embodies a distinct mental model for thinking about computation and writing programs.
Holds
A badly written AI outbound email is evidence of a bad vendor, not of a limit of AI.
Holds
A bigger context window does not give you a smarter model; the intelligence of the model is what decides how much of that window it can actually attend to.
Holds
A body of publications is easy for AI models to consume via pretraining corpora but cumbersome for most humans due to CAPTCHAs, accounts, and paywalls.
Holds
A tiny language model inventing a plausible-sounding name is the same phenomenon as a large one confidently stating a false fact.
Holds
AI should be released iteratively rather than built in secret, because AI and surprise do not go together and the world needs time to adapt before it is under the gun.
Holds
An AI can already earn an A on a university economics midterm, years earlier than informed forecasters expected.
Holds
AI progress is faster than people expect, and ordinary scaling can be enough to solve problems that looked very hard.
Holds
As models keep growing, AI is running out of enough high-quality unique training tokens to keep up.
Holds
Current techniques restrict pre-trained representation power because standard language models are unidirectional.
Holds