Tap a claim on the ring to put it at the centre.
← Neural networks do not have a one-to-one mapping between individual neurons and concepts.
17 connected korrents · 17 moments on record from 10 Jun 2022 to 8 Sept 2026.
Everything filed under LLMs
LLMs
Everything filed under Google
Google
Everything filed under reinforcement learning
reinforcement learning
Everything filed under scaling laws
scaling laws
Everything filed under Psychotherapy
Psychotherapy 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: Neural networks do not have a one-to-one mapping between individual neurons and concepts. Neural networks do not have a one-to-one mapping between individual neurons and concepts. Last stated today
8 Sept 2026
SA
Scott Alexander — holds since 2026-09-08 — tap for who they are
Same subject: The adult brain's stock of neurons is essentially fixed, and that is no limit on learning, because plasticity is the changing of connections between the cells you already have. — tap to centre the map on it The adult brain's stock of neurons is essentially fixed, and that is no limit on learning, because plasticity is the changing of connections between the cells you already have. Last stated 2 months ago
20 Jul 2026
TW
Tommy Wood — holds since 2026-07-20 — tap for who they are
Same subject: Concepts are represented with strikingly similar geometry inside large AI models and inside brains. — tap to centre the map on it Concepts are represented with strikingly similar geometry inside large AI models and inside brains. Last stated 3 weeks ago
20 Aug 2026
MH
Max Hodak — holds since 2026-08-20 — tap for who they are
Same subject: Opening a fixed relational pattern takes two things: the implicit made explicit, and the person's own recoil from what they see. — tap to centre the map on it Opening a fixed relational pattern takes two things: the implicit made explicit, and the person's own recoil from what they see. Last stated 3 years ago
11 Aug 2023
TR
Terry Real — holds since 2023-08-11 — tap for who they are
Same subject: We have almost no automated techniques for making a system transfer what it learns, and none of the few we have are used in modern deep learning. — tap to centre the map on it We have almost no automated techniques for making a system transfer what it learns, and none of the few we have are used in modern deep learning. Last stated 11 months ago
26 Sept 2025
RS
Richard Sutton — holds since 2025-09-26 — tap for who they are
Same subject: The knowledge a model soaks up in pre-training is holding it back; what we actually want is the intelligence with the knowledge stripped out. — tap to centre the map on it The knowledge a model soaks up in pre-training is holding it back; what we actually want is the intelligence with the knowledge stripped out. Last stated 11 months ago
17 Oct 2025
AK
Andrej Karpathy — holds since 2025-10-17 — tap for who they are
Same subject: Anything nature shaped can be learned efficiently by a classical neural network, because evolutionary processes leave structure behind. — tap to centre the map on it Anything nature shaped can be learned efficiently by a classical neural network, because evolutionary processes leave structure behind. Last stated a year ago
23 Jul 2025
DH
Demis Hassabis — holds since 2025-07-23 — tap for who they are
Same subject: Deep properties of a model are inherited through the previous generation's data, which is why AI systems from different companies end up correlated with one another. — tap to centre the map on it Deep properties of a model are inherited through the previous generation's data, which is why AI systems from different companies end up correlated with one another. Last stated 4 weeks ago
11 Aug 2026
RG
Ryan Greenblatt — holds since 2026-08-11 — tap for who they are
Same subject: Aligning an AI is not impossible in principle; the problem is that it has to be done without the textbook that would make it look easy. — tap to centre the map on it Aligning an AI is not impossible in principle; the problem is that it has to be done without the textbook that would make it look easy. Last stated 4 years ago
10 Jun 2022
EY
Eliezer Yudkowsky — holds since 2022-06-10 — tap for who they are
Same subject: A child who has seen ten cats learns what a machine needs the whole internet of cat photos for, by a learning pathway nobody has solved. — tap to centre the map on it A child who has seen ten cats learns what a machine needs the whole internet of cat photos for, by a learning pathway nobody has solved. Last stated 4 weeks ago
10 Aug 2026
FL
Fei-Fei Li — holds since 2026-08-10 — tap for who they are
Same subject: A frontier model is measurably more intelligent with no system prompt at all; the prompts that remain are there for the product, not the model. — tap to centre the map on it A frontier model is measurably more intelligent with no system prompt at all; the prompts that remain are there for the product, not the model. Last stated a month ago
27 Jul 2026
BC
Boris Cherny — holds since 2026-07-27 — tap for who they are
Same subject: A language model is no substitute for a well-specified conventional algorithm, so it cannot simply be dropped into a complex problem and trusted. — tap to centre the map on it A language model is no substitute for a well-specified conventional algorithm, so it cannot simply be dropped into a complex problem and trusted. Last stated a year ago
7 Jun 2025
GM
Gary Marcus — holds since 2025-06-07 — tap for who they are
Same subject: A physical AI company needs three AIs, not one — the agent, the simulator and the critic — turning deployment into a flywheel. — tap to centre the map on it A physical AI company needs three AIs, not one — the agent, the simulator and the critic — turning deployment into a flywheel. Last stated a month ago
3 Aug 2026
DD
Dmitri Dolgov — holds since 2026-08-03 — tap for who they are
Same subject: A verifiable task can be optimised by reinforcement learning until a neural network performs it extremely well. — tap to centre the map on it A verifiable task can be optimised by reinforcement learning until a neural network performs it extremely well. Last stated 10 months ago
17 Nov 2025
AK
Andrej Karpathy — holds since 2025-11-17 — tap for who they are
Same subject: Building a realistic simulator is exactly as hard as building the agent, because the simulator is itself a large AI model. — tap to centre the map on it Building a realistic simulator is exactly as hard as building the agent, because the simulator is itself a large AI model. Last stated a month ago
3 Aug 2026
DD
Dmitri Dolgov — holds since 2026-08-03 — tap for who they are
Same subject: A company's staff-engineer bar should be set against the best companies in the industry rather than against its own history, which is what makes title inflation a real cost. — tap to centre the map on it A company's staff-engineer bar should be set against the best companies in the industry rather than against its own history, which is what makes title inflation a real cost. Last stated 5 months ago
1 Apr 2026
TP
Thuan Pham — holds since 2026-04-01 — tap for who they are
Same subject: A crewed rocket cannot be made safe by making the booster reliable, so the only real way to improve safety is to carry an escape system. — tap to centre the map on it A crewed rocket cannot be made safe by making the booster reliable, so the only real way to improve safety is to carry an escape system. Last stated 3 years ago
14 Dec 2023
JB
Jeff Bezos — holds since 2023-12-14 — tap for who they are
Same subject: A monopolist that can no longer grow by winning new users can only grow by making its product worse for the users it already has. — tap to centre the map on it A monopolist that can no longer grow by winning new users can only grow by making its product worse for the users it already has. Last stated 3 years ago
28 Jul 2023
CD
Cory Doctorow — holds since 2023-07-28 — tap for who they are
At the centre
Neural networks do not have a one-to-one mapping between individual neurons and concepts.
Holds SA Scott AlexanderRead this korrent →
The adult brain's stock of neurons is essentially fixed, and that is no limit on learning, because plasticity is the changing of connections between the cells you already have.
Holds TW Tommy Wood
Concepts are represented with strikingly similar geometry inside large AI models and inside brains.
Holds MH Max Hodak
Opening a fixed relational pattern takes two things: the implicit made explicit, and the person's own recoil from what they see.
Holds TR Terry Real
We have almost no automated techniques for making a system transfer what it learns, and none of the few we have are used in modern deep learning.
Holds RS Richard Sutton
The knowledge a model soaks up in pre-training is holding it back; what we actually want is the intelligence with the knowledge stripped out.
Holds
Anything nature shaped can be learned efficiently by a classical neural network, because evolutionary processes leave structure behind.
Holds DH Demis Hassabis
Deep properties of a model are inherited through the previous generation's data, which is why AI systems from different companies end up correlated with one another.
Holds RG Ryan Greenblatt
Aligning an AI is not impossible in principle; the problem is that it has to be done without the textbook that would make it look easy.
Holds EY Eliezer Yudkowsky
A child who has seen ten cats learns what a machine needs the whole internet of cat photos for, by a learning pathway nobody has solved.
Holds FL Fei-Fei Li
A frontier model is measurably more intelligent with no system prompt at all; the prompts that remain are there for the product, not the model.
Holds
A language model is no substitute for a well-specified conventional algorithm, so it cannot simply be dropped into a complex problem and trusted.
Holds GM Gary Marcus
A physical AI company needs three AIs, not one — the agent, the simulator and the critic — turning deployment into a flywheel.
Holds DD Dmitri Dolgov
A verifiable task can be optimised by reinforcement learning until a neural network performs it extremely well.
Holds
Building a realistic simulator is exactly as hard as building the agent, because the simulator is itself a large AI model.
Holds DD Dmitri Dolgov
A company's staff-engineer bar should be set against the best companies in the industry rather than against its own history, which is what makes title inflation a real cost.
Holds TP Thuan Pham
A crewed rocket cannot be made safe by making the booster reliable, so the only real way to improve safety is to carry an escape system.
Holds JB Jeff Bezos
A monopolist that can no longer grow by winning new users can only grow by making its product worse for the users it already has.
Holds CD Cory Doctorow