Tap a claim on the ring to put it at the centre.
← Nobody knows what is going on inside a large model, and the…
17 connected korrents · 14 moments on record from 28 Oct 2011 to 18 Aug 2026.
Everything filed under mathematics
mathematics
Everything filed under LLMs
LLMs
Everything filed under formal proof
formal proof
Everything filed under AI alignment
AI alignment
Everything filed under AI and science
AI and science 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: Nobody knows what is going on inside a large model, and the interpretability pictures we can draw do not answer the only question that matters. Nobody knows what is going on inside a large model, and the interpretability pictures we can draw do not answer the only question that matters. Last stated 4 years ago
10 Jun 2022
EY
Eliezer Yudkowsky — holds since 2022-06-10 — tap for who they are
Same subject: Biology keeps turning up whole classes of things nobody knew existed, and that is what defeats attempts to model it. — tap to centre the map on it Biology keeps turning up whole classes of things nobody knew existed, and that is what defeats attempts to model it. Last stated 2 years ago
19 Sept 2024
DL
Derek Lowe — holds since 2024-09-19 — tap for who they are
Same subject: Large language models are a bad way to do science, because they have been fed so much that nobody knows what they already knew. — tap to centre the map on it Large language models are a bad way to do science, because they have been fed so much that nobody knows what they already knew. Last stated 11 months ago
26 Sept 2025
RS
Richard Sutton — holds since 2025-09-26 — tap for who they are
Same subject: Models are enormous only because the internet is bad: most of that capacity does memory work, and a better dataset would need far less of it. — tap to centre the map on it Models are enormous only because the internet is bad: most of that capacity does memory work, and a better dataset would need far less of it. Last stated 11 months ago
17 Oct 2025
AK
Andrej Karpathy — holds since 2025-10-17 — tap for who they are
Same subject: What sits in a model's context is far clearer to it than its training data, which is trillions of tokens stirred into a soup of parameters. — tap to centre the map on it What sits in a model's context is far clearer to it than its training data, which is trillions of tokens stirred into a soup of parameters. Last stated a month ago
30 Jul 2026
JD
Jeff Dean — holds since 2026-07-30 — tap for who they are
Same subject: Large language models are bad at chess: pattern recognition is not the same capability as searching one position very deeply. — tap to centre the map on it Large language models are bad at chess: pattern recognition is not the same capability as searching one position very deeply. Last stated 11 months ago
5 Oct 2025
AC
Albert Cheng — holds since 2025-10-05 — tap for who they are
Same subject: Large language models do not reason formally: their performance collapses as a problem is made bigger, in the way a calculator's never does. — tap to centre the map on it Large language models do not reason formally: their performance collapses as a problem is made bigger, in the way a calculator's never does. Last stated 2 years ago
11 Oct 2024
GM
Gary Marcus — holds since 2024-10-11 — tap for who they are
Same subject: Machine learning is a shallow field compared with mathematics: even its most important ideas can be explained in a couple of minutes. — tap to centre the map on it Machine learning is a shallow field compared with mathematics: even its most important ideas can be explained in a couple of minutes. Last stated 4 weeks ago
11 Aug 2026
RG
Ryan Greenblatt — holds since 2026-08-11 — tap for who they are
Same subject: Alignment of today's models is going well enough to look solvable, while aligning models we can no longer understand remains unsolved. — tap to centre the map on it Alignment of today's models is going well enough to look solvable, while aligning models we can no longer understand remains unsolved. Last stated 8 months ago
22 Jan 2026
JL
Jan Leike — holds since 2026-01-22 — tap for who they are
Same subject: A proof and an explanation are different things, and a theorem can stay an unsolved expository problem long after it is proved. — tap to centre the map on it A proof and an explanation are different things, and a theorem can stay an unsolved expository problem long after it is proved. Last stated 2 months ago
30 Jun 2026
GS
Grant Sanderson — holds since 2026-06-30 — tap for who they are
Same subject: A stream of AI-written papers with any error rate at all becomes insufferable, because finding the error costs more than the paper is worth even at ninety-nine percent. — tap to centre the map on it A stream of AI-written papers with any error rate at all becomes insufferable, because finding the error costs more than the paper is worth even at ninety-nine percent. Last stated 2 months ago
30 Jun 2026
GS
Grant Sanderson — holds since 2026-06-30 — tap for who they are
Same subject: Academic credentials — grades, major, the prestige of the degree — barely matter to industry hiring. — tap to centre the map on it Academic credentials — grades, major, the prestige of the degree — barely matter to industry hiring. Last stated 15 years ago
28 Oct 2011
PM
Patrick McKenzie — holds since 2011-10-28 — tap for who they are
Same subject: Formalising a proof in Lean currently takes about ten times the effort of writing it out: doable, but annoying. — tap to centre the map on it Formalising a proof in Lean currently takes about ten times the effort of writing it out: doable, but annoying. Last stated a year ago
14 Jun 2025
TT
Terence Tao — holds since 2025-06-14 — tap for who they are
Same subject: Full formal verification is a waste of money for most software: near-perfect is reachable with ordinary techniques at a fraction of the cost. — tap to centre the map on it Full formal verification is a waste of money for most software: near-perfect is reachable with ordinary techniques at a fraction of the cost. Last stated 8 years ago
21 Jan 2019
HW
Hillel Wayne — holds since 2019-01-21 — tap for who they are
Same subject: Lean and tools like GitHub will let experimental mathematics scale far beyond what one mathematician's spaghetti code allows today. — tap to centre the map on it Lean and tools like GitHub will let experimental mathematics scale far beyond what one mathematician's spaghetti code allows today. Last stated a year ago
14 Jun 2025
TT
Terence Tao — holds since 2025-06-14 — tap for who they are
Same subject: AI could compete with human mathematicians once it acquires a mathematical sense of smell: knowing which way of splitting a problem makes it easier rather than harder. — tap to centre the map on it AI could compete with human mathematicians once it acquires a mathematical sense of smell: knowing which way of splitting a problem makes it easier rather than harder. Last stated a year ago
14 Jun 2025
TT
Terence Tao — holds since 2025-06-14 — tap for who they are
Same subject: AI in chess and mathematics does not explain anything; it says which position is better, and humans build the theory from that. — tap to centre the map on it AI in chess and mathematics does not explain anything; it says which position is better, and humans build the theory from that. Last stated a year ago
14 Jun 2025
LF
Lex Fridman — holds since 2025-06-14 — tap for who they are
Same subject: AI will transform how scientific discovery is done, and within two or three years a working scientist's job will already look dramatically different. — tap to centre the map on it AI will transform how scientific discovery is done, and within two or three years a working scientist's job will already look dramatically different. Last stated 3 weeks ago
18 Aug 2026
MK
Michael Kratsios — holds since 2026-08-18 — tap for who they are
At the centre
Nobody knows what is going on inside a large model, and the interpretability pictures we can draw do not answer the only question that matters.
Holds EY Eliezer YudkowskyRead this korrent →
Biology keeps turning up whole classes of things nobody knew existed, and that is what defeats attempts to model it.
Holds DL Derek Lowe
Large language models are a bad way to do science, because they have been fed so much that nobody knows what they already knew.
Holds RS Richard Sutton
Models are enormous only because the internet is bad: most of that capacity does memory work, and a better dataset would need far less of it.
Holds
What sits in a model's context is far clearer to it than its training data, which is trillions of tokens stirred into a soup of parameters.
Holds JD Jeff Dean
Large language models are bad at chess: pattern recognition is not the same capability as searching one position very deeply.
Holds AC Albert Cheng
Large language models do not reason formally: their performance collapses as a problem is made bigger, in the way a calculator's never does.
Holds GM Gary Marcus
Machine learning is a shallow field compared with mathematics: even its most important ideas can be explained in a couple of minutes.
Holds RG Ryan Greenblatt
Alignment of today's models is going well enough to look solvable, while aligning models we can no longer understand remains unsolved.
Holds JL Jan Leike
A proof and an explanation are different things, and a theorem can stay an unsolved expository problem long after it is proved.
Holds GS Grant Sanderson
A stream of AI-written papers with any error rate at all becomes insufferable, because finding the error costs more than the paper is worth even at ninety-nine percent.
Holds GS Grant Sanderson
Academic credentials — grades, major, the prestige of the degree — barely matter to industry hiring.
Holds PM Patrick McKenzie
Formalising a proof in Lean currently takes about ten times the effort of writing it out: doable, but annoying.
Holds TT Terence Tao
Full formal verification is a waste of money for most software: near-perfect is reachable with ordinary techniques at a fraction of the cost.
Holds HW Hillel Wayne
Lean and tools like GitHub will let experimental mathematics scale far beyond what one mathematician's spaghetti code allows today.
Holds TT Terence Tao
AI could compete with human mathematicians once it acquires a mathematical sense of smell: knowing which way of splitting a problem makes it easier rather than harder.
Holds TT Terence Tao
AI in chess and mathematics does not explain anything; it says which position is better, and humans build the theory from that.
Holds LF Lex Fridman
AI will transform how scientific discovery is done, and within two or three years a working scientist's job will already look dramatically different.
Holds MK Michael Kratsios