Tap a claim on the ring to put it at the centre.
← A small enough winning ticket learns faster than the network it was cut out of, and ends up more accurate than it.
17 connected korrents · 13 moments on record from 9 Mar 2018 to 30 Jul 2026.
Everything filed under pruning
pruning
Everything filed under batteries
batteries
Everything filed under energy
energy
Everything filed under neural networks
neural networks
Everything filed under benchmarks
benchmarks
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: A small enough winning ticket learns faster than the network it was cut out of, and ends up more accurate than it. A small enough winning ticket learns faster than the network it was cut out of, and ends up more accurate than it. Last stated 9 years ago
9 Mar 2018
MC
Michael Carbin — holds since 2018-03-09 — tap for who they are
JF
Jonathan Frankle — holds since 2018-03-09 — tap for who they are
Same subject: A winning ticket wins on its initial weights: the connections it keeps started at values that happen to make training work. — tap to centre the map on it A winning ticket wins on its initial weights: the connections it keeps started at values that happen to make training work. Last stated 9 years ago
9 Mar 2018
MC
Michael Carbin — holds since 2018-03-09 — tap for who they are
JF
Jonathan Frankle — holds since 2018-03-09 — tap for who they are
Same subject: Batteries will replace transmission as the cheapest way to keep the lights on, and the grid will shrink rather than grow. — tap to centre the map on it Batteries will replace transmission as the cheapest way to keep the lights on, and the grid will shrink rather than grow. Last stated 9 months ago
8 Dec 2025
CH
Casey Handmer — holds since 2023-10-11 — tap for who they are
CH
Casey Handmer — holds since 2025-12-08 — tap for who they are
Same subject: Neuroplasticity is as much the removal of connections as the growth of new ones, so pruning is a form of learning rather than a form of decay. — tap to centre the map on it Neuroplasticity is as much the removal of connections as the growth of new ones, so pruning is a form of learning rather than a form of decay. Last stated 2 months ago
20 Jul 2026
TW
Tommy Wood — holds since 2026-07-20 — tap for who they are
Same subject: Pruning cuts the parameters of a trained network by over 90% without costing accuracy, so inference gets smaller and faster for free. — tap to centre the map on it Pruning cuts the parameters of a trained network by over 90% without costing accuracy, so inference gets smaller and faster for free. Last stated 9 years ago
9 Mar 2018
MC
Michael Carbin — holds since 2018-03-09 — tap for who they are
JF
Jonathan Frankle — holds since 2018-03-09 — tap for who they are
Same subject: Pruning does not merely shrink a network; it uncovers subnetworks whose original initialization was what made them trainable at all. — tap to centre the map on it Pruning does not merely shrink a network; it uncovers subnetworks whose original initialization was what made them trainable at all. Last stated 9 years ago
9 Mar 2018
MC
Michael Carbin — holds since 2018-03-09 — tap for who they are
JF
Jonathan Frankle — holds since 2018-03-09 — tap for who they are
Same subject: The saving pruning offers is only ever at inference, because the sparse architectures it produces are hard to train from the start. — tap to centre the map on it The saving pruning offers is only ever at inference, because the sparse architectures it produces are hard to train from the start. Last stated 9 years ago
9 Mar 2018
MC
Michael Carbin — holds since 2018-03-09 — tap for who they are
JF
Jonathan Frankle — holds since 2018-03-09 — tap for who they are
Same subject: Running a model five times and keeping the best answer buys a higher benchmark score without buying a better model. — tap to centre the map on it Running a model five times and keeping the best answer buys a higher benchmark score without buying a better model. Last stated 2 months ago
26 Jun 2026
NB
Noam Brown — holds since 2026-06-26 — tap for who they are
Same subject: Learned approximations of slow simulators change what science is possible, by turning a six-month screening run into something you do over lunch. — tap to centre the map on it Learned approximations of slow simulators change what science is possible, by turning a six-month screening run into something you do over lunch. Last stated a month ago
30 Jul 2026
JD
Jeff Dean — holds since 2026-07-30 — 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: Access to large-scale generalist AI systems that could be weaponized should be limited, meaning their code and neural network parameters should not be released open-source. — tap to centre the map on it Access to large-scale generalist AI systems that could be weaponized should be limited, meaning their code and neural network parameters should not be released open-source. Last stated 3 years ago
24 Jun 2023
YB
Yoshua Bengio — holds since 2023-06-24 — tap for who they are
Same subject: An agent can understand a maximally simplified explanation and still be unable to come up with it — that gap is what is left of the expert's job. — tap to centre the map on it An agent can understand a maximally simplified explanation and still be unable to come up with it — that gap is what is left of the expert's job. Last stated 6 months ago
20 Mar 2026
AK
Andrej Karpathy — holds since 2026-03-20 — tap for who they are
Same subject: A data centre powered by solar and batteries alone needs an array so oversized that the design is not worth building. — tap to centre the map on it A data centre powered by solar and batteries alone needs an array so oversized that the design is not worth building. Last stated 2 years ago
18 Apr 2024
AV
Austin Vernon — holds since 2024-04-18 — tap for who they are
Same subject: About a fifth of the US grid could be freed for data centres just by covering the yearly peak with batteries or peaker plants. — tap to centre the map on it About a fifth of the US grid could be freed for data centres just by covering the yearly peak with batteries or peaker plants. Last stated 6 months ago
13 Mar 2026
DP
Dylan Patel — holds since 2026-03-13 — tap for who they are
Same subject: An off-grid data centre can delete its uninterruptible power supplies entirely, because the battery bank outside already is one. — tap to centre the map on it An off-grid data centre can delete its uninterruptible power supplies entirely, because the battery bank outside already is one. Last stated 2 years ago
18 Apr 2024
AV
Austin Vernon — holds since 2024-04-18 — tap for who they are
Same subject: "Food from thin air" is not from thin air: it runs on water, minerals, ammonia and industrial plant. — tap to centre the map on it "Food from thin air" is not from thin air: it runs on water, minerals, ammonia and industrial plant. Last stated 2 months ago
30 Jun 2026
CS
Chris Smaje — holds since 2026-06-30 — tap for who they are
Same subject: A country outside the AI supply chain should just buy the index — which works only in the world where AI ends up commoditised rather than concentrated. — tap to centre the map on it A country outside the AI supply chain should just buy the index — which works only in the world where AI ends up commoditised rather than concentrated. Last stated 3 months ago
4 Jun 2026
AI
Alex Imas — holds since 2026-06-04 — tap for who they are
Same subject: A future of constrained energy will need more people working the land, and that is not the same as going back to the past. — tap to centre the map on it A future of constrained energy will need more people working the land, and that is not the same as going back to the past. Last stated 2 months ago
30 Jun 2026
CS
Chris Smaje — holds since 2026-06-30 — tap for who they are
At the centre
A small enough winning ticket learns faster than the network it was cut out of, and ends up more accurate than it.
Holds MC Michael CarbinJF Jonathan FrankleRead this korrent →
A winning ticket wins on its initial weights: the connections it keeps started at values that happen to make training work.
Holds MC Michael CarbinJF Jonathan Frankle
Batteries will replace transmission as the cheapest way to keep the lights on, and the grid will shrink rather than grow.
Holds CH Casey Handmer
Neuroplasticity is as much the removal of connections as the growth of new ones, so pruning is a form of learning rather than a form of decay.
Holds TW Tommy Wood
Pruning cuts the parameters of a trained network by over 90% without costing accuracy, so inference gets smaller and faster for free.
Holds MC Michael CarbinJF Jonathan Frankle
Pruning does not merely shrink a network; it uncovers subnetworks whose original initialization was what made them trainable at all.
Holds MC Michael CarbinJF Jonathan Frankle
The saving pruning offers is only ever at inference, because the sparse architectures it produces are hard to train from the start.
Holds MC Michael CarbinJF Jonathan Frankle
Running a model five times and keeping the best answer buys a higher benchmark score without buying a better model.
Holds NB Noam Brown
Learned approximations of slow simulators change what science is possible, by turning a six-month screening run into something you do over lunch.
Holds JD Jeff Dean
A verifiable task can be optimised by reinforcement learning until a neural network performs it extremely well.
Holds
Access to large-scale generalist AI systems that could be weaponized should be limited, meaning their code and neural network parameters should not be released open-source.
Holds
An agent can understand a maximally simplified explanation and still be unable to come up with it — that gap is what is left of the expert's job.
Holds
A data centre powered by solar and batteries alone needs an array so oversized that the design is not worth building.
Holds AV Austin Vernon
About a fifth of the US grid could be freed for data centres just by covering the yearly peak with batteries or peaker plants.
Holds DP Dylan Patel
An off-grid data centre can delete its uninterruptible power supplies entirely, because the battery bank outside already is one.
Holds AV Austin Vernon
"Food from thin air" is not from thin air: it runs on water, minerals, ammonia and industrial plant.
Holds CS Chris Smaje
A country outside the AI supply chain should just buy the index — which works only in the world where AI ends up commoditised rather than concentrated.
Holds AI Alex Imas
A future of constrained energy will need more people working the land, and that is not the same as going back to the past.
Holds CS Chris Smaje