Tap a claim on the ring to put it at the centre.
← Photographing a moment can weaken your memory of it, because the…
17 connected korrents · 14 moments from 2 Dec 2002 to 10 Sept 2026.
Everything filed under neural networks
neural networks
Everything filed under pruning
pruning
Everything filed under prompt injection
prompt injection
Everything filed under documentation
documentation
Everything filed under taste
taste
Everything filed under education
education 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: Photographing a moment can weaken your memory of it, because the reason you took the picture was not to have to remember. Photographing a moment can weaken your memory of it, because the reason you took the picture was not to have to remember. Last stated 3 months ago
13 Jul 2026
AC
Alan Castel — holds since 2026-07-13 — tap for who they are
Same subject: The problem is not remembering through photographs but remembering only the photographs, which eclipses other understanding — tap to centre the map on it The problem is not remembering through photographs but remembering only the photographs, which eclipses other understanding Last stated 24 years ago
2 Dec 2002
SS
Susan Sontag — holds since 2002-12-02 — tap for who they are
Same subject: There is no such thing as photographic memory: people with exceptional visual memory still make ordinary memory errors. — tap to centre the map on it There is no such thing as photographic memory: people with exceptional visual memory still make ordinary memory errors. Last stated 3 months ago
13 Jul 2026
AC
Alan Castel — holds since 2026-07-13 — tap for who they are
Same subject: 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. — tap to centre the map on it 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: You should never choose your own photos, because nobody knows what they actually look like. — tap to centre the map on it You should never choose your own photos, because nobody knows what they actually look like. Last stated 2 years ago
20 Aug 2024
PL
Pieter Levels — holds since 2024-08-20 — tap for who they are
Same subject: Picking someone out of a lineup overwrites the memory of the face actually seen, so identification makes a witness more confident and less accurate at the same time. — tap to centre the map on it Picking someone out of a lineup overwrites the memory of the face actually seen, so identification makes a witness more confident and less accurate at the same time. Last stated 3 months ago
13 Jul 2026
AC
Alan Castel — holds since 2026-07-13 — 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: Photographs do not represent the world the way human perception actually experiences it. — tap to centre the map on it Photographs do not represent the world the way human perception actually experiences it. Last stated a month ago
10 Sept 2026
HK
Henrik Karlsson — holds since 2026-09-10 — 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: A deep bidirectional model is strictly more powerful than a left-to-right model or a shallow concatenation of unidirectional models. — tap to centre the map on it A deep bidirectional model is strictly more powerful than a left-to-right model or a shallow concatenation of unidirectional models. 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: A layer should learn a residual with reference to its own input rather than an unreferenced function, which is what makes great depth trainable. — tap to centre the map on it A layer should learn a residual with reference to its own input rather than an unreferenced function, which is what makes great depth trainable. Last stated 11 years ago
10 Dec 2015
JS
Jian Sun — holds since 2015-12-10 — tap for who they are
KH
Kaiming He — holds since 2015-12-10 — tap for who they are
Same subject: A neural network's latent space is closer to an uncopyrightable syntax than to copyrightable expression. — tap to centre the map on it A neural network's latent space is closer to an uncopyrightable syntax than to copyrightable expression. Last stated 2 months ago
7 Sept 2026
KK
Kevin Kelly — holds since 2026-09-07 — tap for who they are
Same subject: Auto-mode does not yet convincingly fix prompt-injection risk for coding agents. — tap to centre the map on it Auto-mode does not yet convincingly fix prompt-injection risk for coding agents. Last stated 2 months ago
8 Aug 2026
SW
Simon Willison — holds since 2026-08-08 — tap for who they are
Same subject: For agents built on Claude Fable 5.1, it is in practice safe for now to assume they will not get prompt injected. — tap to centre the map on it For agents built on Claude Fable 5.1, it is in practice safe for now to assume they will not get prompt injected. Last stated 2 months ago
4 Sept 2026
ZM
Zvi Mowshowitz — holds since 2026-09-04 — tap for who they are
Same subject: Prompt injection can be caught by watching the neurons that fire when it happens, so a defence no longer depends on the model reporting the attack. — tap to centre the map on it Prompt injection can be caught by watching the neurons that fire when it happens, so a defence no longer depends on the model reporting the attack. Last stated 3 months ago
27 Jul 2026
BC
Boris Cherny — holds since 2026-07-27 — tap for who they are
At the centre
Photographing a moment can weaken your memory of it, because the reason you took the picture was not to have to remember.
Holds Read this korrent →
The problem is not remembering through photographs but remembering only the photographs, which eclipses other understanding
Holds
There is no such thing as photographic memory: people with exceptional visual memory still make ordinary memory errors.
Holds
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
You should never choose your own photos, because nobody knows what they actually look like.
Holds
Picking someone out of a lineup overwrites the memory of the face actually seen, so identification makes a witness more confident and less accurate at the same time.
Holds
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
Photographs do not represent the world the way human perception actually experiences it.
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
A deep bidirectional model is strictly more powerful than a left-to-right model or a shallow concatenation of unidirectional models.
Holds
A layer should learn a residual with reference to its own input rather than an unreferenced function, which is what makes great depth trainable.
Holds
A neural network's latent space is closer to an uncopyrightable syntax than to copyrightable expression.
Holds
Auto-mode does not yet convincingly fix prompt-injection risk for coding agents.
Holds
For agents built on Claude Fable 5.1, it is in practice safe for now to assume they will not get prompt injected.
Holds
Prompt injection can be caught by watching the neurons that fire when it happens, so a defence no longer depends on the model reporting the attack.
Holds