korrents

On the map

Tap a claim on the ring to put it at the centre.

← Deep learning generalises badly, and catastrophic interference with what a network already knew is the proof of it.

17 connected korrents · 18 moments from 1 Jun 2009 to 16 Oct 2026.

Everything filed under neural networks neural networks Everything filed under computer vision computer vision Everything filed under pruning pruning Everything filed under AI alignment AI alignment Everything filed under design design Everything filed under mathematics mathematics Everything filed under LLMs LLMs Everything filed under transformers transformers Same subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Read this korrent: Deep learning generalises badly, and catastrophic interference with what a network already knew is the proof of it. Deep learning generalises badly, andcatastrophic interference with what anetwork already knew is the proof of it. Last stated a year ago 26 Sept 2025 RS Richard Sutton — holds since 2025-09-26 — 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 inpre-training is holding it back;what we actually want is theintelligence with the knowledgestripped out. Last stated a year ago 17 Oct 2025 AK Andrej Karpathy — holds since 2025-10-17 — tap for who they are Same subject: AI systems keep trying hard outside training because a model that only exerted itself when it detected training would be useless and would be selected away. — tap to centre the map on it AI systems keep trying hard outsidetraining because a model that onlyexerted itself when it detectedtraining would be useless and wouldbe selected away. Last stated 2 months ago 1 Sept 2026 AC Ajeya Cotra — holds since 2026-09-01 — tap for who they are Same subject: Generative AI has failed to produce the learning gains it was promised to deliver and instead shows evidence of harming learning. — tap to centre the map on it Generative AI has failed to producethe learning gains it was promisedto deliver and instead showsevidence of harming learning. Last stated 4 months ago 24 Jun 2026 DM Dan Meyer — holds since 2026-06-24 — tap for who they are Same subject: Deep learning will be understood very differently in thirty years than it is today. — tap to centre the map on it Deep learning will be understoodvery differently in thirty yearsthan it is today. Last stated 11 years ago 3 Sept 2015 CO Christopher Olah — holds since 2015-09-03 — tap for who they are Same subject: Work on large language models is not progress toward artificial general intelligence, because the models do not understand what they read. — tap to centre the map on it Work on large language models is notprogress toward artificial generalintelligence, because the models donot understand what they read. Last stated a year ago 30 Jul 2025 AG Alexey Guzey — holds since 2024-08-09 — tap for who they are AG Alexey Guzey — no longer holds since 2025-07-30 — tap for who they are Same subject: Machine learning is a shallow field compared with mathematics: even its most important ideas can be explained in a couple of minutes. — tap to centre the map on it Machine learning is a shallow fieldcompared with mathematics: even itsmost important ideas can beexplained in a couple of minutes. Last stated 2 months ago 11 Aug 2026 RG Ryan Greenblatt — holds since 2026-08-11 — tap for who they are Same subject: It may be the case that neural networks will never be perfectly explainable in a way that satisfies human rationality. — tap to centre the map on it It may be the case that neuralnetworks will never be perfectlyexplainable in a way that satisfieshuman rationality. Last stated a week ago 16 Oct 2026 DB Dean W. Ball — holds since 2026-10-16 — tap for who they are Same subject: Large language models are a bad way to do science, because they have been fed so much that nobody knows what they already knew. — tap to centre the map on it Large language models are a bad wayto do science, because they havebeen fed so much that nobody knowswhat they already knew. Last stated a year ago 26 Sept 2025 RS Richard Sutton — holds since 2025-09-26 — 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 transmissionas the cheapest way to keep thelights on, and the grid will shrinkrather 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: 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 somepruning during context compactionanyway for cost reasons, which Jevmight 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 theremoval of connections as the growthof new ones, so pruning is a form oflearning rather than a form ofdecay. Last stated 3 months ago 20 Jul 2026 TW Tommy Wood — holds since 2026-07-20 — tap for who they are Same subject: Sequence transduction can use a simple architecture based solely on attention, without recurrence or convolutions. — tap to centre the map on it Sequence transduction can use asimple architecture based solely onattention, without recurrence orconvolutions. Last stated 9 years ago 12 Jun 2017 IP Illia Polosukhin — holds since 2017-06-12 — tap for who they are JU Jakob Uszkoreit — holds since 2017-06-12 — tap for who they are NP Niki Parmar — holds since 2017-06-12 — tap for who they are AV Ashish Vaswani — holds since 2017-06-12 — tap for who they are NS Noam Shazeer — holds since 2017-06-12 — tap for who they are AG Aidan N. Gomez — holds since 2017-06-12 — tap for who they are +2 2 more Same subject: A transduction model can rely entirely on self-attention for input and output representations without sequence-aligned RNNs or convolution. — tap to centre the map on it A transduction model can relyentirely on self-attention for inputand output representations withoutsequence-aligned RNNs orconvolution. Last stated 9 years ago 12 Jun 2017 IP Illia Polosukhin — holds since 2017-06-12 — tap for who they are JU Jakob Uszkoreit — holds since 2017-06-12 — tap for who they are NP Niki Parmar — holds since 2017-06-12 — tap for who they are AV Ashish Vaswani — holds since 2017-06-12 — tap for who they are NS Noam Shazeer — holds since 2017-06-12 — tap for who they are AG Aidan N. Gomez — holds since 2017-06-12 — tap for who they are +2 2 more Same subject: Looped/recurrent-depth transformer architectures can improve model quality at a fixed compute budget when the model is large enough. — tap to centre the map on it Looped/recurrent-depth transformerarchitectures can improve modelquality at a fixed compute budgetwhen the model is large enough. Last stated a month ago 9 Sept 2026 SR Sebastian Raschka — holds since 2026-09-09 — 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 notcomputer vision but the discovery ofa universal function approximatorthat 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 unifypixel generation and pixelreconstruction, two tracks computervision has kept apart for over halfa 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 canenable more sophisticated models forindexing and interacting withmultimedia. Last stated 17 years ago 1 Jun 2009 FL Fei-Fei Li — holds since 2009-06-01 — tap for who they are
same subject or similar wordinga cloud: claims about one subject, named for itbar: when it was last stated, on a scale from 2009 to today (stretched back to the oldest claim here) — full is todaya face: someone who holds the claim — tap it for who they arefaded, dashed ring: they no longer hold it — they changed their mind

At the centre Deep learning generalises badly, and catastrophic interference with what a network already knew is the proof of it. Last stated 26 Sept 2025 · a year ago Holds Richard Sutton Read this korrent →