korrents

On the map

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

← Sparse autoencoders are a useful interpretability tool but are often…

14 connected korrents · 13 moments on record from 1 Jan 1998 to 7 Sept 2026.

Everything filed under neural networks neural networks Everything filed under pruning pruning Everything filed under computer vision computer vision Everything filed under education education Everything filed under coding agents coding agents Same subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Read this korrent: Sparse autoencoders are a useful interpretability tool but are often used wastefully when a simpler, more obvious method would work as well or better Sparse autoencoders are a usefulinterpretability tool but are often usedwastefully when a simpler, more obviousmethod would work as well or better Last stated a year ago 19 Aug 2025 NN Neel Nanda — holds since 2025-08-19 — 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 onlyever at inference, because thesparse architectures it produces arehard 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: As models get better at following instructions, techniques like finetuning and constrained sampling for structured outputs will become less necessary — tap to centre the map on it As models get better at followinginstructions, techniques likefinetuning and constrained samplingfor structured outputs will becomeless necessary Last stated 3 years ago 16 Jan 2024 CH Chip Huyen — holds since 2024-01-16 — tap for who they are Same subject: Complete reverse-engineering of neural networks is a less promising research direction than studying model biology and applying interpretability usefully — tap to centre the map on it Complete reverse-engineering ofneural networks is a less promisingresearch direction than studyingmodel biology and applyinginterpretability usefully Last stated a year ago 19 Aug 2025 NN Neel Nanda — holds since 2025-08-19 — tap for who they are Same subject: The most underused thing AI does is teach you: people reach for it to write their code and forget it can take them through a curriculum in an hour. — tap to centre the map on it The most underused thing AI does isteach you: people reach for it towrite their code and forget it cantake them through a curriculum in anhour. Last stated a year ago 21 Sept 2025 JZ Julie Zhuo — holds since 2025-09-21 — tap for who they are Same subject: Locality is what makes a language good for AI: if a single file states what it imports and what it offers, a model never has to hold the whole program at once. — tap to centre the map on it Locality is what makes a languagegood for AI: if a single file stateswhat it imports and what it offers,a model never has to hold the wholeprogram at once. Last stated 4 months ago 13 May 2026 AH Anders Hejlsberg — holds since 2026-05-13 — 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 isstrictly more powerful than aleft-to-right model or a shallowconcatenation of unidirectionalmodels. 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 withreference to its own input ratherthan an unreferenced function, whichis 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 iscloser to an uncopyrightable syntaxthan to copyrightable expression. Last stated 2 weeks ago 7 Sept 2026 KK Kevin Kelly — holds since 2026-09-07 — 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 learnsfaster than the network it was cutout of, and ends up more accuratethan 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 initialweights: the connections it keepsstarted at values that happen tomake 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 transmissionas the cheapest way to keep thelights on, and the grid will shrinkrather 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: 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 2 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 weeks ago 4 Sept 2026 FL Fei-Fei Li — holds since 2026-09-04 — tap for who they are Same subject: Graph transformer networks allow multimodule document recognition systems to be trained globally with gradient methods to minimize overall performance. — tap to centre the map on it Graph transformer networks allowmultimodule document recognitionsystems to be trained globally withgradient methods to minimize overallperformance. Last stated 29 years ago 1 Jan 1998 YB Yoshua Bengio — holds since 1998-01-01 — 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 1998 to today (stretched back to the oldest claim here) — full is todaya face: someone on record holding the claim — tap it for who they are

At the centre Sparse autoencoders are a useful interpretability tool but are often used wastefully when a simpler, more obvious method would work as well or better Last stated 19 Aug 2025 · a year ago Holds Neel Nanda Read this korrent →