korrents

On the map

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

← TF32 is essentially free if you can tolerate a small loss of…

17 connected korrents · 15 moments from 10 Dec 2015 to 25 Oct 2026.

Everything filed under neural networks neural networks Everything filed under LLMs LLMs Everything filed under vibe coding vibe coding Everything filed under SaaS SaaS Everything filed under design design Same subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Read this korrent: TF32 is essentially free if you can tolerate a small loss of precision, and empirically training with it is indistinguishable. TF32 is essentially free if you cantolerate a small loss of precision, andempirically training with it isindistinguishable. Last stated 2 years ago 9 Jun 2024 AK Andrej Karpathy — holds since 2024-06-09 — tap for who they are Same subject: With AI, software distribution is "less than free": people can build exactly what they need instead of getting it. — tap to centre the map on it With AI, software distribution is"less than free": people can buildexactly what they need instead ofgetting it. Last stated 4 weeks ago 25 Oct 2026 SS Sam Schillace — holds since 2026-10-25 — tap for who they are Same subject: A freemium product's free tier should sample everything the paid product can do, because a limited free experience teaches users the product is limited. — tap to centre the map on it A freemium product's free tiershould sample everything the paidproduct can do, because a limitedfree experience teaches users theproduct is limited. Last stated a year ago 5 Oct 2025 AC Albert Cheng — holds since 2025-10-05 — tap for who they are Same subject: Training in fp16 required gradient scaling, which is annoying and an extra source of state and complexity. — tap to centre the map on it Training in fp16 required gradientscaling, which is annoying and anextra source of state andcomplexity. Last stated 2 years ago 9 Jun 2024 AK Andrej Karpathy — holds since 2024-06-09 — tap for who they are Same subject: Distillation carries a higher risk of overfitting, so it is not a free lunch. — tap to centre the map on it Distillation carries a higher riskof overfitting, so it is not a freelunch. Last stated a month ago 17 Oct 2026 SR Sebastian Raschka — holds since 2026-10-17 — tap for who they are Same subject: An answer computed by a Python program deserves more trust than a language model's mental arithmetic. — tap to centre the map on it An answer computed by a Pythonprogram deserves more trust than alanguage model's mental arithmetic. Last stated 2 years ago 5 Feb 2025 AK Andrej Karpathy — holds since 2025-02-05 — tap for who they are Same subject: Figma is still important, but using it to dial in full fidelity is probably the wrong use, because it is not the actual code base. — tap to centre the map on it Figma is still important, but usingit to dial in full fidelity isprobably the wrong use, because itis not the actual code base. Last stated 8 months ago 12 Mar 2026 JP Josh Puckett — holds since 2026-03-12 — tap for who they are Same subject: At the level of loss functions, language-model pre-training is remarkably simple, though running it at scale is a complete engineering feat. — tap to centre the map on it At the level of loss functions,language-model pre-training isremarkably simple, though running itat scale is a complete engineeringfeat. Last stated 4 months ago 16 Jul 2026 GS Grant Sanderson — holds since 2026-07-16 — tap for who they are Same subject: If you use language models professionally and a cheaper model is not smart enough, it is worth paying for the top tier. — tap to centre the map on it If you use language modelsprofessionally and a cheaper modelis not smart enough, it is worthpaying for the top tier. Last stated 2 years ago 27 Feb 2025 AK Andrej Karpathy — holds since 2025-02-27 — tap for who they are Same subject: A curve, which is what a deep learning model is, is a very bad substrate for discrete computation. — tap to centre the map on it A curve, which is what a deeplearning model is, is a very badsubstrate for discrete computation. Last stated 2 years ago 6 Nov 2024 FC François Chollet — holds since 2024-11-06 — 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 project-level agent memory file works like a neural net, steering the agent much as a fine-tuned LoRA steers a model. — tap to centre the map on it A project-level agent memory fileworks like a neural net, steeringthe agent much as a fine-tuned LoRAsteers a model. Last stated 3 months ago 23 Aug 2026 KC Kun Chen — holds since 2026-08-23 — 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: Intelligence is the execution of small, simplicity-weighted programs found by search over smooth loss landscapes in overparameterized networks, approaching Bayes-optimal reasoning as scale increases. — tap to centre the map on it Intelligence is the execution ofsmall, simplicity-weighted programsfound by search over smooth losslandscapes in overparameterizednetworks, approaching Bayes-optimalreasoning as scale increases. Last stated 5 years ago 11 Jun 2021 GW Gwern — holds since 2021-06-11 — tap for who they are 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: Linear probes are very strong classifiers, and attention-head probes are even stronger. — tap to centre the map on it Linear probes are very strongclassifiers, and attention-headprobes are even stronger. Last stated 11 months ago 20 Dec 2025 NN Neel Nanda — holds since 2025-12-20 — tap for who they are Same subject: Self-attention can yield more interpretable models. — tap to centre the map on it Self-attention can yield moreinterpretable models. 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 or similar wordinga cloud: claims about one subject, named for itbar: when it was last stated, on a scale from 2015 to today — full is todaya face: someone who holds the claim — tap it for who they are

At the centre TF32 is essentially free if you can tolerate a small loss of precision, and empirically training with it is indistinguishable. Last stated 9 Jun 2024 · 2 years ago Holds Andrej Karpathy Read this korrent →