Tap a claim on the ring to put it at the centre.
← Model comparisons understate real progress, because benchmark tables…
17 connected korrents · 16 moments from 3 Oct 2012 to 19 Sept 2026. Nearly all of them are about scaling laws .
Everything filed under benchmarks
benchmarks
Everything filed under LLMs
LLMs
Everything filed under AGI
AGI
Everything filed under reinforcement learning
reinforcement learning
Everything filed under AI agents
AI agents 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: Model comparisons understate real progress, because benchmark tables do not control for how much test-time compute each answer used. Model comparisons understate real progress, because benchmark tables do not control for how much test-time compute each answer used. Last stated 4 months ago
26 Jun 2026
NB
Noam Brown — holds since 2026-06-26 — tap for who they are
Same subject: A benchmark result should be reported under a stated budget, or as a curve against test-time compute — never as a single number. — tap to centre the map on it A benchmark result should be reported under a stated budget, or as a curve against test-time compute — never as a single number. Last stated 4 months ago
26 Jun 2026
NB
Noam Brown — holds since 2026-06-26 — tap for who they are
Same subject: Language models perform better on benchmark problems released before their training data cutoff, indicating data contamination inflates scores. — tap to centre the map on it Language models perform better on benchmark problems released before their training data cutoff, indicating data contamination inflates scores. Last stated 2 years ago
13 May 2024
SR
Sebastian Ruder — holds since 2024-05-13 — tap for who they are
Same subject: A lab should spend most of its compute on research rather than on building the next model, because research is where the tenfold yearly efficiency gains come from. — tap to centre the map on it A lab should spend most of its compute on research rather than on building the next model, because research is where the tenfold yearly efficiency gains come from. Last stated 7 months ago
13 Mar 2026
DP
Dylan Patel — holds since 2026-03-13 — tap for who they are
Same subject: After pre-training, post-training and test-time scaling, the fourth scaling law is agentic: multiplying AI by spawning agents, and the whole loop scales on one thing, compute. — tap to centre the map on it After pre-training, post-training and test-time scaling, the fourth scaling law is agentic: multiplying AI by spawning agents, and the whole loop scales on one thing, compute. Last stated 7 months ago
23 Mar 2026
JH
Jensen Huang — holds since 2026-03-23 — tap for who they are
Same subject: AI scaling laws require exponentially more compute and resources to produce only linear gains in model intelligence. — tap to centre the map on it AI scaling laws require exponentially more compute and resources to produce only linear gains in model intelligence. Last stated a month ago
19 Sept 2026
NL
Nathan Lambert — holds since 2026-09-19 — tap for who they are
Same subject: As models keep scaling up, modularity will become essential to how they are developed. — tap to centre the map on it As models keep scaling up, modularity will become essential to how they are developed. Last stated 4 years ago
23 Feb 2023
SR
Sebastian Ruder — holds since 2023-02-23 — tap for who they are
Same subject: Bet on a system that is maximally learned and minimally constrained, and add structure only where it improves the scaling laws. — tap to centre the map on it Bet on a system that is maximally learned and minimally constrained, and add structure only where it improves the scaling laws. Last stated 3 months ago
3 Aug 2026
DD
Dmitri Dolgov — holds since 2026-08-03 — tap for who they are
Same subject: Current AI techniques are four to six orders of magnitude away from optimal in data efficiency and test-time compute efficiency. — tap to centre the map on it Current AI techniques are four to six orders of magnitude away from optimal in data efficiency and test-time compute efficiency. Last stated 2 months ago
7 Aug 2026
FC
François Chollet — holds since 2026-08-07 — 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 feedback loop that reinforces a behavior pulls it toward whatever improves the loop's own score. — tap to centre the map on it A feedback loop that reinforces a behavior pulls it toward whatever improves the loop's own score. Last stated 2 months ago
26 Aug 2026
HK
Henrik Karlsson — holds since 2026-08-26 — 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 3 months 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 11 months ago
17 Nov 2025
AK
Andrej Karpathy — holds since 2025-11-17 — tap for who they are
Same subject: A true artificial general intelligence cannot exist without being recognized as a moral subject. — tap to centre the map on it A true artificial general intelligence cannot exist without being recognized as a moral subject. Last stated a year ago
10 Jun 2025
SH
Samuel Hammond — holds since 2025-06-10 — tap for who they are
Same subject: AGI research made no progress in its first six decades. — tap to centre the map on it AGI research made no progress in its first six decades. Last stated 14 years ago
3 Oct 2012
DD
David Deutsch — holds since 2012-10-03 — tap for who they are
Same subject: An AI that cannot work out new physics has not equalled human intelligence, let alone surpassed it, because humans have worked out new physics. — tap to centre the map on it An AI that cannot work out new physics has not equalled human intelligence, let alone surpassed it, because humans have worked out new physics. Last stated 3 years ago
9 Nov 2023
EM
Elon Musk — holds since 2023-11-09 — tap for who they are
At the centre
Model comparisons understate real progress, because benchmark tables do not control for how much test-time compute each answer used.
Holds Read this korrent →
A benchmark result should be reported under a stated budget, or as a curve against test-time compute — never as a single number.
Holds
Language models perform better on benchmark problems released before their training data cutoff, indicating data contamination inflates scores.
Holds
A lab should spend most of its compute on research rather than on building the next model, because research is where the tenfold yearly efficiency gains come from.
Holds
After pre-training, post-training and test-time scaling, the fourth scaling law is agentic: multiplying AI by spawning agents, and the whole loop scales on one thing, compute.
Holds
AI scaling laws require exponentially more compute and resources to produce only linear gains in model intelligence.
Holds
As models keep scaling up, modularity will become essential to how they are developed.
Holds
Bet on a system that is maximally learned and minimally constrained, and add structure only where it improves the scaling laws.
Holds
Current AI techniques are four to six orders of magnitude away from optimal in data efficiency and test-time compute efficiency.
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 feedback loop that reinforces a behavior pulls it toward whatever improves the loop's own score.
Holds
A physical AI company needs three AIs, not one — the agent, the simulator and the critic — turning deployment into a flywheel.
Holds
A verifiable task can be optimised by reinforcement learning until a neural network performs it extremely well.
Holds
A true artificial general intelligence cannot exist without being recognized as a moral subject.
Holds
AGI research made no progress in its first six decades.
Holds
An AI that cannot work out new physics has not equalled human intelligence, let alone surpassed it, because humans have worked out new physics.
Holds