Tap a claim on the ring to put it at the centre.
← The point of a good memory is not to remember more but to remember…
17 connected korrents · 9 moments from 9 Mar 2018 to 1 Sept 2026.
Everything filed under pruning
pruning
Everything filed under batteries
batteries
Everything filed under education
education
Everything filed under developer tools
developer tools
Everything filed under curiosity
curiosity
Everything filed under Apple
Apple 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: The point of a good memory is not to remember more but to remember better, because forgetting most of what you experience is what human brains are built to do. The point of a good memory is not to remember more but to remember better, because forgetting most of what you experience is what human brains are built to do. Last stated 2 years ago
25 May 2024
CR
Charan Ranganath — holds since 2024-05-25 — tap for who they are
Same subject: Seeing something many times does not put it into memory: familiarity with a thing and knowledge of it are different, and people confuse the two constantly. — tap to centre the map on it Seeing something many times does not put it into memory: familiarity with a thing and knowledge of it are different, and people confuse the two constantly. Last stated 3 months ago
13 Jul 2026
AC
Alan Castel — holds since 2026-07-13 — tap for who they are
Same subject: Spaced recall works by stripping a memory of the time and place it happened, which is why the memories you revisit most feel like facts you read rather than things you lived. — tap to centre the map on it Spaced recall works by stripping a memory of the time and place it happened, which is why the memories you revisit most feel like facts you read rather than things you lived. Last stated 2 years ago
25 May 2024
CR
Charan Ranganath — holds since 2024-05-25 — tap for who they are
Same subject: In APIs and command-line tools, having fewer ways to accomplish the same task is better because it reduces how much a person has to remember. — tap to centre the map on it In APIs and command-line tools, having fewer ways to accomplish the same task is better because it reduces how much a person has to remember. Last stated 2 months ago
1 Sept 2026
NJ
Nick Janetakis — holds since 2026-09-01 — tap for who they are
Same subject: Forgetting is a feature of a working memory system rather than a failure of it. — tap to centre the map on it Forgetting is a feature of a working memory system rather than a failure of it. Last stated 3 months ago
13 Jul 2026
AC
Alan Castel — holds since 2026-07-13 — tap for who they are
Same subject: Having both episodic and semantic memory is what lets a mind change on a dime without erasing what it already learned, and it is why humans can learn from so little data. — tap to centre the map on it Having both episodic and semantic memory is what lets a mind change on a dime without erasing what it already learned, and it is why humans can learn from so little data. Last stated 2 years ago
25 May 2024
CR
Charan Ranganath — holds since 2024-05-25 — tap for who they are
Same subject: Older adults are not worse rememberers so much as more selective ones: they keep what they were curious about and let the rest go. — tap to centre the map on it Older adults are not worse rememberers so much as more selective ones: they keep what they were curious about and let the rest go. Last stated 3 months ago
13 Jul 2026
AC
Alan Castel — holds since 2026-07-13 — tap for who they are
Same subject: Confidence in a memory is not evidence of its accuracy, and our sense of how our own memory works is systematically wrong. — tap to centre the map on it Confidence in a memory is not evidence of its accuracy, and our sense of how our own memory works is systematically wrong. Last stated 3 months ago
13 Jul 2026
AC
Alan Castel — holds since 2026-07-13 — tap for who they are
Same subject: You only retain what you were pushed to your limit on: if learning feels like coasting, you are not learning. — tap to centre the map on it You only retain what you were pushed to your limit on: if learning feels like coasting, you are not learning. Last stated 2 years ago
25 May 2024
CR
Charan Ranganath — holds since 2024-05-25 — tap for who they are
Same subject: A small enough winning ticket learns faster than the network it was cut out of, and ends up more accurate than it. — tap to centre the map on 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 10 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: Intelligence is the execution of small, simplicity-weighted programs found by search over smooth loss landscapes in overparameterized networks, approaching Bayes-optimal reasoning as scale increases. — tap to centre the map on it Intelligence is the execution of small, simplicity-weighted programs found by search over smooth loss landscapes in overparameterized networks, approaching Bayes-optimal reasoning as scale increases. Last stated 5 years ago
11 Jun 2021
GW
Gwern — holds since 2021-06-11 — 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: 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 3 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 7 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 3 years ago
18 Apr 2024
AV
Austin Vernon — holds since 2024-04-18 — tap for who they are
At the centre
The point of a good memory is not to remember more but to remember better, because forgetting most of what you experience is what human brains are built to do.
Holds Read this korrent →
Seeing something many times does not put it into memory: familiarity with a thing and knowledge of it are different, and people confuse the two constantly.
Holds
Spaced recall works by stripping a memory of the time and place it happened, which is why the memories you revisit most feel like facts you read rather than things you lived.
Holds
In APIs and command-line tools, having fewer ways to accomplish the same task is better because it reduces how much a person has to remember.
Holds
Forgetting is a feature of a working memory system rather than a failure of it.
Holds
Having both episodic and semantic memory is what lets a mind change on a dime without erasing what it already learned, and it is why humans can learn from so little data.
Holds
Older adults are not worse rememberers so much as more selective ones: they keep what they were curious about and let the rest go.
Holds
Confidence in a memory is not evidence of its accuracy, and our sense of how our own memory works is systematically wrong.
Holds
You only retain what you were pushed to your limit on: if learning feels like coasting, you are not learning.
Holds
A small enough winning ticket learns faster than the network it was cut out of, and ends up more accurate than it.
Holds
A winning ticket wins on its initial weights: the connections it keeps started at values that happen to make training work.
Holds
Batteries will replace transmission as the cheapest way to keep the lights on, and the grid will shrink rather than grow.
Holds
Intelligence is the execution of small, simplicity-weighted programs found by search over smooth loss landscapes in overparameterized networks, approaching Bayes-optimal reasoning as scale increases.
Holds
Pruning cuts the parameters of a trained network by over 90% without costing accuracy, so inference gets smaller and faster for free.
Holds
Pruning does not merely shrink a network; it uncovers subnetworks whose original initialization was what made them trainable at all.
Holds
A data centre powered by solar and batteries alone needs an array so oversized that the design is not worth building.
Holds
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
An off-grid data centre can delete its uninterruptible power supplies entirely, because the battery bank outside already is one.
Holds