Tap a claim on the ring to put it at the centre.
← Recurrent backpropagation learns slowly over long intervals mainly because error backflow decays.
17 connected korrents · 17 moments from 1 Nov 1997 to 18 Sept 2026.
Everything filed under neural networks
neural networks
Everything filed under pruning
pruning
Everything filed under LLMs
LLMs
Everything filed under computer vision
computer vision
Everything filed under AI agents
AI agents
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: Recurrent backpropagation learns slowly over long intervals mainly because error backflow decays. Recurrent backpropagation learns slowly over long intervals mainly because error backflow decays. Last stated 29 years ago
1 Nov 1997
JS
Jürgen Schmidhuber — holds since 1997-11-01 — tap for who they are
SH
Sepp Hochreiter — holds since 1997-11-01 — tap for who they are
Same subject: Standard recurrent neural networks are theoretically capable of representing long-term dependencies but fail to learn them from data in practice. — tap to centre the map on it Standard recurrent neural networks are theoretically capable of representing long-term dependencies but fail to learn them from data in practice. Last stated 11 years ago
27 Aug 2015
CO
Christopher Olah — holds since 2015-08-27 — tap for who they are
Same subject: LSTM architectures are designed so that retaining information over long time spans is their default behavior rather than something they must struggle to learn. — tap to centre the map on it LSTM architectures are designed so that retaining information over long time spans is their default behavior rather than something they must struggle to learn. Last stated 11 years ago
27 Aug 2015
CO
Christopher Olah — holds since 2015-08-27 — tap for who they are
Same subject: Growing evidence suggests the brain performs a form of backpropagation-like learning. — tap to centre the map on it Growing evidence suggests the brain performs a form of backpropagation-like learning. Last stated 6 years ago
13 Mar 2021
GW
Gwern — holds since 2021-03-13 — tap for who they are
Same subject: Long-running agents fail because they drift off the distribution they were trained on, and degrade further the farther out they get. — tap to centre the map on it Long-running agents fail because they drift off the distribution they were trained on, and degrade further the farther out they get. Last stated 3 months ago
30 Jul 2026
JD
Jeff Dean — holds since 2026-07-30 — tap for who they are
Same subject: Anything nature shaped can be learned efficiently by a classical neural network, because evolutionary processes leave structure behind. — tap to centre the map on it Anything nature shaped can be learned efficiently by a classical neural network, because evolutionary processes leave structure behind. Last stated a year ago
23 Jul 2025
DH
Demis Hassabis — holds since 2025-07-23 — tap for who they are
Same subject: The knowledge a model soaks up in pre-training is holding it back; what we actually want is the intelligence with the knowledge stripped out. — tap to centre the map on it The knowledge a model soaks up in pre-training is holding it back; what we actually want is the intelligence with the knowledge stripped out. Last stated a year ago
17 Oct 2025
AK
Andrej Karpathy — holds since 2025-10-17 — 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: 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 3 months ago
30 Jul 2026
JD
Jeff Dean — holds since 2026-07-30 — 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 11 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: Most agent harnesses need some pruning during context compaction anyway for cost reasons, which Jev might help with. — tap to centre the map on it Most agent harnesses need some pruning during context compaction anyway for cost reasons, which Jev might help with. Last stated a month ago
18 Sept 2026
AR
Armin Ronacher — holds since 2026-09-18 — 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 3 months ago
20 Jul 2026
TW
Tommy Wood — holds since 2026-07-20 — tap for who they are
Same subject: As reasoning models and agents retain more tokens for longer, KV-cache size and attention cost become the main constraint on scaling context. — tap to centre the map on it As reasoning models and agents retain more tokens for longer, KV-cache size and attention cost become the main constraint on scaling context. Last stated 5 months ago
16 May 2026
SR
Sebastian Raschka — holds since 2026-05-16 — tap for who they are
Same subject: Context engineering has stayed relevant for a year because it is grounded in how transformer attention works, and it will matter to anyone building on AI until post-transformer models arrive. — tap to centre the map on it Context engineering has stayed relevant for a year because it is grounded in how transformer attention works, and it will matter to anyone building on AI until post-transformer models arrive. Last stated 3 months ago
15 Jul 2026
DH
Dex Horthy — holds since 2026-07-15 — tap for who they are
Same subject: Directly optimizing prompt embeddings (prefix-tuning) yields better performance than even a single optimized text prompt. — tap to centre the map on it Directly optimizing prompt embeddings (prefix-tuning) yields better performance than even a single optimized text prompt. Last stated 6 years ago
4 Feb 2021
GW
Gwern — holds since 2021-02-04 — tap for who they are
Same subject: AlexNet's real breakthrough was not computer vision but the discovery of a universal function approximator that can learn any function. — tap to centre the map on it AlexNet's real breakthrough was not computer vision but the discovery of a universal function approximator that can learn any function. Last stated 3 months ago
26 Jul 2026
JH
Jensen Huang — holds since 2026-07-26 — tap for who they are
Same subject: Atlas is the first model to unify pixel generation and pixel reconstruction, two tracks computer vision has kept apart for over half a century. — tap to centre the map on it Atlas is the first model to unify pixel generation and pixel reconstruction, two tracks computer vision has kept apart for over half a century. Last stated 2 months ago
4 Sept 2026
FL
Fei-Fei Li — holds since 2026-09-04 — tap for who they are
Same subject: Growth of internet image data can enable more sophisticated models for indexing and interacting with multimedia. — tap to centre the map on it Growth of internet image data can enable more sophisticated models for indexing and interacting with multimedia. Last stated 17 years ago
1 Jun 2009
FL
Fei-Fei Li — holds since 2009-06-01 — tap for who they are
At the centre
Recurrent backpropagation learns slowly over long intervals mainly because error backflow decays.
Holds Read this korrent →
Standard recurrent neural networks are theoretically capable of representing long-term dependencies but fail to learn them from data in practice.
Holds
LSTM architectures are designed so that retaining information over long time spans is their default behavior rather than something they must struggle to learn.
Holds
Growing evidence suggests the brain performs a form of backpropagation-like learning.
Holds
Long-running agents fail because they drift off the distribution they were trained on, and degrade further the farther out they get.
Holds
Anything nature shaped can be learned efficiently by a classical neural network, because evolutionary processes leave structure behind.
Holds
The knowledge a model soaks up in pre-training is holding it back; what we actually want is the intelligence with the knowledge stripped out.
Holds
The saving pruning offers is only ever at inference, because the sparse architectures it produces are hard to train from the start.
Holds
Learned approximations of slow simulators change what science is possible, by turning a six-month screening run into something you do over lunch.
Holds
Batteries will replace transmission as the cheapest way to keep the lights on, and the grid will shrink rather than grow.
Holds
Most agent harnesses need some pruning during context compaction anyway for cost reasons, which Jev might help with.
Holds
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
As reasoning models and agents retain more tokens for longer, KV-cache size and attention cost become the main constraint on scaling context.
Holds
Context engineering has stayed relevant for a year because it is grounded in how transformer attention works, and it will matter to anyone building on AI until post-transformer models arrive.
Holds
Directly optimizing prompt embeddings (prefix-tuning) yields better performance than even a single optimized text prompt.
Holds
AlexNet's real breakthrough was not computer vision but the discovery of a universal function approximator that can learn any function.
Holds
Atlas is the first model to unify pixel generation and pixel reconstruction, two tracks computer vision has kept apart for over half a century.
Holds
Growth of internet image data can enable more sophisticated models for indexing and interacting with multimedia.
Holds