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…

17 connected korrents · 17 moments from 1 Apr 1946 to 15 Sept 2026.

Everything filed under simplicity simplicity Everything filed under LLMs LLMs Everything filed under pruning pruning Everything filed under neural networks neural networks Everything filed under coding agents coding agents Same subjectSame subjectSame subjectSame 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: Auto-regressive LLMs are useful as writing and coding aids but hallucinate too often — tap to centre the map on it Auto-regressive LLMs are useful aswriting and coding aids buthallucinate too often Last stated 4 years ago 26 Mar 2023 YL Yann LeCun — holds since 2023-03-26 — 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: Refusing to engage with AI tools leads to being mistaken about their strengths and limitations. — tap to centre the map on it Refusing to engage with AI toolsleads to being mistaken about theirstrengths and limitations. Last stated 5 months ago 26 May 2026 KP Kelsey Piper — holds since 2026-05-26 — tap for who they are Same subject: Current AI models do not actually understand things and still hallucinate. — tap to centre the map on it Current AI models do not actuallyunderstand things and stillhallucinate. Last stated a year ago 13 Oct 2025 SG Saul Griffith — holds since 2025-10-13 — 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 6 months ago 13 May 2026 AH Anders Hejlsberg — holds since 2026-05-13 — tap for who they are Same subject: A browser works better as a single window than as multiple separate windows. — tap to centre the map on it A browser works better as a singlewindow than as multiple separatewindows. Last stated 2 months ago 15 Sept 2026 CC Chris Coyier — holds since 2026-09-15 — tap for who they are Same subject: A business is more likely to fail from taking on too much complexity than from lacking resources. — tap to centre the map on it A business is more likely to failfrom taking on too much complexitythan from lacking resources. Last stated 8 years ago 29 Sept 2018 TG Tren Griffin — holds since 2018-09-29 — tap for who they are Same subject: A business succeeds through a small number of highly effective distribution channels, not many mediocre ones. — tap to centre the map on it A business succeeds through a smallnumber of highly effectivedistribution channels, not manymediocre ones. Last stated 3 years ago 17 Feb 2024 AW Adam Wiggins — holds since 2024-02-17 — tap for who they are Same subject: A design has to be kept simple for reliability and intellectual control, but nobody yet knows how to reach simplicity systematically. — tap to centre the map on it A design has to be kept simple forreliability and intellectualcontrol, but nobody yet knows how toreach simplicity systematically. Last stated 28 years ago 1 Mar 1999 ED Edsger W. Dijkstra — holds since 1999-03-01 — tap for who they are Same subject: A designer's edge now is pulling things back, making them simpler and more understandable, because everyone can kind of execute right now. — tap to centre the map on it A designer's edge now is pullingthings back, making them simpler andmore understandable, becauseeveryone can kind of execute rightnow. Last stated 3 months ago 29 Jul 2026 CD Charlie Deets — holds since 2026-07-29 — tap for who they are Same subject: A feature only truly reaches billions of users when they do not have to think about a switch or a mode. — tap to centre the map on it A feature only truly reachesbillions of users when they do nothave to think about a switch or amode. Last stated 3 months ago 16 Aug 2026 IS Ian Silber — holds since 2026-08-16 — tap for who they are Same subject: Communicating clearly is less about the number of words used and more about focusing on the right ideas and directions. — tap to centre the map on it Communicating clearly is less aboutthe number of words used and moreabout focusing on the right ideasand directions. Last stated 3 years ago 3 Jan 2024 TS Tobias Sjösten — holds since 2024-01-03 — tap for who they are Same subject: If you simplify your English, a stupid remark becomes obviously stupid, even to yourself. — tap to centre the map on it If you simplify your English, astupid remark becomes obviouslystupid, even to yourself. Last stated 81 years ago 1 Apr 1946 GO George Orwell — holds since 1946-04-01 — tap for who they are Same subject: Most music writing in the internet age should consist only of a link and a brief recommendation. — tap to centre the map on it Most music writing in the internetage should consist only of a linkand a brief recommendation. Last stated 2 months ago 7 Sept 2026 RP Rick Perlstein — holds since 2026-09-07 — 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 1946 to today (stretched back to the oldest claim here) — full is todaya face: someone who holds 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 →