Tap a claim on the ring to put it at the centre.
← When pre-training data is limited, it is better to train a smaller…
17 connected korrents · 18 moments from 29 Sept 2018 to 19 Sept 2026. Nearly all of them are about scaling laws .
Everything filed under LLMs
LLMs
Everything filed under simplicity
simplicity
Everything filed under benchmarks
benchmarks
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: When pre-training data is limited, it is better to train a smaller model for multiple epochs than to train a larger model on unique data once. When pre-training data is limited, it is better to train a smaller model for multiple epochs than to train a larger model on unique data once. Last stated 3 years ago
1 Dec 2023
SR
Sebastian Ruder — holds since 2023-12-01 — 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: 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 8 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 2 months 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 3 months ago
7 Aug 2026
FC
François Chollet — holds since 2026-08-07 — 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
Same subject: In instruction tuning, a smaller set of high-quality training examples outperforms a larger, noisier dataset. — tap to centre the map on it In instruction tuning, a smaller set of high-quality training examples outperforms a larger, noisier dataset. Last stated 3 years ago
15 Nov 2023
SR
Sebastian Ruder — holds since 2023-11-15 — tap for who they are
Same subject: LLMs cannot be expected to undertake the significant task of managing complexity of their own volition because they do not operate under constraints of time or load. — tap to centre the map on it LLMs cannot be expected to undertake the significant task of managing complexity of their own volition because they do not operate under constraints of time or load. Last stated 7 months ago
12 Apr 2026
BC
Bryan Cantrill — holds since 2026-04-12 — tap for who they are
Same subject: There is unmet demand for a single, well-integrated local AI model experience, rather than a patchwork of local AI components. — tap to centre the map on it There is unmet demand for a single, well-integrated local AI model experience, rather than a patchwork of local AI components. Last stated 6 months ago
14 May 2026
SS
Salvatore Sanfilippo — holds since 2026-05-14 — tap for who they are
Same subject: A browser works better as a single window than as multiple separate windows. — tap to centre the map on it A browser works better as a single window than as multiple separate windows. Last stated 2 months ago
15 Sept 2026
CC
Chris Coyier — holds since 2026-09-15 — tap for who they are
Same subject: A business is more likely to fail from taking on too much complexity than from lacking resources. — tap to centre the map on it A business is more likely to fail from taking on too much complexity than from lacking resources. Last stated 8 years ago
29 Sept 2018
TG
Tren Griffin — holds since 2018-09-29 — tap for who they are
Same subject: A business succeeds through a small number of highly effective distribution channels, not many mediocre ones. — tap to centre the map on it A business succeeds through a small number of highly effective distribution channels, not many mediocre ones. Last stated 3 years ago
17 Feb 2024
AW
Adam Wiggins — holds since 2024-02-17 — 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 9 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
At the centre
When pre-training data is limited, it is better to train a smaller model for multiple epochs than to train a larger model on unique data once.
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
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
Current techniques restrict pre-trained representation power because standard language models are unidirectional.
Holds
In instruction tuning, a smaller set of high-quality training examples outperforms a larger, noisier dataset.
Holds
LLMs cannot be expected to undertake the significant task of managing complexity of their own volition because they do not operate under constraints of time or load.
Holds
There is unmet demand for a single, well-integrated local AI model experience, rather than a patchwork of local AI components.
Holds
A browser works better as a single window than as multiple separate windows.
Holds
A business is more likely to fail from taking on too much complexity than from lacking resources.
Holds
A business succeeds through a small number of highly effective distribution channels, not many mediocre ones.
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