Tap a claim on the ring to put it at the centre.
← If reasoning can be separated from facts, the frontier labs lose their…
17 connected korrents · 15 moments on record from 3 Jan 2024 to 3 Sept 2026.
Everything filed under benchmarks
benchmarks
Everything filed under Japan
Japan
Everything filed under reinforcement learning
reinforcement learning
Everything filed under scaling laws
scaling laws
Everything filed under Anthropic
Anthropic
Everything filed under physics
physics
Everything filed under semiconductors
semiconductors
Everything filed under LLMs
LLMs 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: If reasoning can be separated from facts, the frontier labs lose their advantage, because nobody needs a million-GPU cluster any more. If reasoning can be separated from facts, the frontier labs lose their advantage, because nobody needs a million-GPU cluster any more. Last stated 2 years ago
19 Jun 2024
AS
Aravind Srinivas — holds since 2024-06-19 — tap for who they are
Same subject: Nvidia's real miss was not seeing that a frontier lab could never be funded by venture capital, so its compute suppliers had to become its investors. — tap to centre the map on it Nvidia's real miss was not seeing that a frontier lab could never be funded by venture capital, so its compute suppliers had to become its investors. Last stated 5 months ago
15 Apr 2026
JH
Jensen Huang — holds since 2026-04-15 — tap for who they are
Same subject: A frontier lab should not spend its researchers harvesting results out of today's models; the payoff is in building the next one. — tap to centre the map on it A frontier lab should not spend its researchers harvesting results out of today's models; the payoff is in building the next one. Last stated 2 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 6 months ago
13 Mar 2026
DP
Dylan Patel — holds since 2026-03-13 — tap for who they are
Same subject: Inference is a high-margin business even for a middleman: renting GPUs at scale, some models carry an eighty per cent margin over their sticker price. — tap to centre the map on it Inference is a high-margin business even for a middleman: renting GPUs at scale, some models carry an eighty per cent margin over their sticker price. Last stated 3 months ago
27 May 2026
DR
Dax Raad — holds since 2026-05-27 — tap for who they are
Same subject: There is no private evidence behind frontier-lab confidence in fast AI progress; the evidence is public and outsiders have simply not absorbed it. — tap to centre the map on it There is no private evidence behind frontier-lab confidence in fast AI progress; the evidence is public and outsiders have simply not absorbed it. Last stated 2 years ago
20 Dec 2024
MB
Miles Brundage — holds since 2024-12-20 — tap for who they are
Same subject: Falling back to older 7-nanometre chips would not rescue AI compute, because the real gap between chip generations is twentyfold, not the threefold the flops suggest. — tap to centre the map on it Falling back to older 7-nanometre chips would not rescue AI compute, because the real gap between chip generations is twentyfold, not the threefold the flops suggest. Last stated 6 months ago
13 Mar 2026
DP
Dylan Patel — holds since 2026-03-13 — tap for who they are
Same subject: There will be no overnight intelligence explosion, because a model's best work takes so much test-time compute that time itself is the bottleneck. — tap to centre the map on it There will be no overnight intelligence explosion, because a model's best work takes so much test-time compute that time itself is the bottleneck. Last stated 2 months ago
26 Jun 2026
NB
Noam Brown — holds since 2026-06-26 — tap for who they are
Same subject: A swarm of untrusted volunteers on the internet could improve models and run circles around the frontier labs, because the earth has far more compute than they do. — tap to centre the map on it A swarm of untrusted volunteers on the internet could improve models and run circles around the frontier labs, because the earth has far more compute than they do. Last stated 6 months ago
20 Mar 2026
AK
Andrej Karpathy — holds since 2026-03-20 — 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: Capability does not generalise for free: a model that will move mountains on an agentic task still tells the same bad joke it told five years ago. — tap to centre the map on it Capability does not generalise for free: a model that will move mountains on an agentic task still tells the same bad joke it told five years ago. Last stated 6 months ago
20 Mar 2026
AK
Andrej Karpathy — holds since 2026-03-20 — tap for who they are
Same subject: Humans barely use reinforcement learning for intelligence — what RL they do use goes into motor tasks, not problem solving. — tap to centre the map on it Humans barely use reinforcement learning for intelligence — what RL they do use goes into motor tasks, not problem solving. Last stated 11 months ago
17 Oct 2025
AK
Andrej Karpathy — holds since 2025-10-17 — tap for who they are
Same subject: A benchmark that ranks Claude Code last while it stays first in use is measuring the wrong thing, and has been for a year. — tap to centre the map on it A benchmark that ranks Claude Code last while it stays first in use is measuring the wrong thing, and has been for a year. Last stated 5 days ago
3 Sept 2026
DR
Dax Raad — holds since 2026-09-03 — 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 speed difference between languages that share the LLVM backend measures the benchmark author, not the languages. — tap to centre the map on it A speed difference between languages that share the LLVM backend measures the benchmark author, not the languages. Last stated a year ago
22 Mar 2025
TH
ThePrimeagen — holds since 2025-03-22 — tap for who they are
Same subject: American shipyards are unproductive rather than expensive: their workers are paid about what Korean and Japanese shipyard workers are paid. — tap to centre the map on it American shipyards are unproductive rather than expensive: their workers are paid about what Korean and Japanese shipyard workers are paid. Last stated 3 years ago
3 Jan 2024
AV
Austin Vernon — holds since 2024-01-03 — tap for who they are
Same subject: Commercial shipbuilding keeps moving to whichever country has the cheapest labour, and America has never been that country. — tap to centre the map on it Commercial shipbuilding keeps moving to whichever country has the cheapest labour, and America has never been that country. Last stated 2 years ago
5 Sept 2024
BP
Brian Potter — holds since 2024-09-05 — tap for who they are
Same subject: Factory-built construction has not raised productivity: the countries that prefabricate most, Sweden and Japan, have had flat construction productivity for decades. — tap to centre the map on it Factory-built construction has not raised productivity: the countries that prefabricate most, Sweden and Japan, have had flat construction productivity for decades. Last stated 9 months ago
11 Dec 2025
BP
Brian Potter — holds since 2025-12-11 — tap for who they are
At the centre
If reasoning can be separated from facts, the frontier labs lose their advantage, because nobody needs a million-GPU cluster any more.
Holds AS Aravind SrinivasRead this korrent →
Nvidia's real miss was not seeing that a frontier lab could never be funded by venture capital, so its compute suppliers had to become its investors.
Holds JH Jensen Huang
A frontier lab should not spend its researchers harvesting results out of today's models; the payoff is in building the next one.
Holds NB Noam Brown
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 DP Dylan Patel
Inference is a high-margin business even for a middleman: renting GPUs at scale, some models carry an eighty per cent margin over their sticker price.
Holds
There is no private evidence behind frontier-lab confidence in fast AI progress; the evidence is public and outsiders have simply not absorbed it.
Holds MB Miles Brundage
Falling back to older 7-nanometre chips would not rescue AI compute, because the real gap between chip generations is twentyfold, not the threefold the flops suggest.
Holds DP Dylan Patel
There will be no overnight intelligence explosion, because a model's best work takes so much test-time compute that time itself is the bottleneck.
Holds NB Noam Brown
A swarm of untrusted volunteers on the internet could improve models and run circles around the frontier labs, because the earth has far more compute than they do.
Holds
A verifiable task can be optimised by reinforcement learning until a neural network performs it extremely well.
Holds
Capability does not generalise for free: a model that will move mountains on an agentic task still tells the same bad joke it told five years ago.
Holds
Humans barely use reinforcement learning for intelligence — what RL they do use goes into motor tasks, not problem solving.
Holds
A benchmark that ranks Claude Code last while it stays first in use is measuring the wrong thing, and has been for a year.
Holds
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 speed difference between languages that share the LLVM backend measures the benchmark author, not the languages.
Holds TH ThePrimeagen
American shipyards are unproductive rather than expensive: their workers are paid about what Korean and Japanese shipyard workers are paid.
Holds AV Austin Vernon
Commercial shipbuilding keeps moving to whichever country has the cheapest labour, and America has never been that country.
Holds BP Brian Potter
Factory-built construction has not raised productivity: the countries that prefabricate most, Sweden and Japan, have had flat construction productivity for decades.
Holds BP Brian Potter