pull down to refresh

Hill Space: Neural nets that do perfect arithmetic (to 10⁻¹⁶ precision)hillspace.justindujardin.com/
230 sats \ 0 comments \ @carter 14 Jul AI
related
AI mimics neocortex computations with 'winner-take-all' approachtechxplore.com/news/2024-10-ai-mimics-neocortex-winner-approach.html
49 sats \ 0 comments \ @ch0k1 26 Oct 2024 tech
Gemma 3 270M: Compact model for hyper-efficient AIdevelopers.googleblog.com/en/introducing-gemma-3-270m/
21 sats \ 0 comments \ @hn 14 Aug tech
tinygrad: A simple and powerful neural network frameworktinygrad.org/
10 sats \ 1 comment \ @premitive1 15 Aug 2023 tech
FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AIepochai.org/frontiermath/the-benchmark
203 sats \ 0 comments \ @Rsync25 10 Nov 2024 tech
Peano arithmetic is enough, because Peano arithmetic encodes computationmath.stackexchange.com/a/5075056/6708
10 sats \ 0 comments \ @hn 14 Jun tech
Implementing Neural Networks in TensorFlow (and PyTorch)towardsdatascience.com/implementing-neural-networks-in-tensorflow-and-pytorch-3c1f097e412a
55 sats \ 1 comment \ @ch0k1 9 Jul 2024 devs
Making The Smallest And Dumbest LLM With Extreme Quantizationhackaday.com/2025/10/23/making-the-smallest-and-dumbest-llm-with-extreme-quantization/
200 sats \ 0 comments \ @0xbitcoiner 24 Oct AI
Testing AI systems on hard math problems shows they still perform very poorlyphys.org/news/2024-11-ai-hard-math-problems-poorly.html
153 sats \ 4 comments \ @south_korea_ln 13 Nov 2024 science
Kolmogorov-Arnold networks may make neural networks more understandablewww.quantamagazine.org/novel-architecture-makes-neural-networks-more-understandable-20240911/
20 sats \ 0 comments \ @hn 12 Sep 2024 tech
New chip opens door to AI computing at light speedbrisk.news/read/articles:psgo5y37lqs36kmzh6qo
1078 sats \ 1 comment \ @GlobalThreat 17 Feb 2024 news
No More Floating Points, The Era of 1.58-bit Large Language Modelsmedium.com/ai-insights-cobet/no-more-floating-points-the-era-of-1-58-bit-large-language-models-b9805879ac0a
100 sats \ 1 comment \ @0xbitcoiner 11 Mar 2024 science freebie
‘Mind-blowing’ IBM chip speeds up AIwww.nature.com/articles/d41586-023-03267-0
41 sats \ 0 comments \ @owleyedapprentice 23 Oct 2023 tech
Continuous Thought Machinesarxiv.org/pdf/2505.05522
162 sats \ 2 comments \ @carter 28 Jun AI
Why Deep Learning Works Unreasonably Wellwww.youtube.com/watch?v=qx7hirqgfuU
100 sats \ 1 comment \ @carter 11 Aug AI
Practical Deep Learning for Coders - Practical Deep Learningcourse.fast.ai/
163 sats \ 0 comments \ @Chep 29 Jul 2024 builders
AI is approaching an open-source inflection point.www.ft.com/content/2968d132-e2b1-490a-9022-3cfe0e1dc0d8
76 sats \ 0 comments \ @ch0k1 25 Jul 2024 news
Compute Where It Counts: High Quality Sparsely Activated LLMscrystalai.org/blog/2025-08-18-compute-where-it-counts
100 sats \ 0 comments \ @carter 21 Aug AI
What Every User Should Know About Mixed Precision Training in PyTorchpytorch.org/blog/what-every-user-should-know-about-mixed-precision-training-in-pytorch/
10 sats \ 1 comment \ @hn 15 Mar 2024 tech
Neural network training makes beautiful fractalssohl-dickstein.github.io/2024/02/12/fractal.html
31 sats \ 0 comments \ @south_korea_ln 13 Feb 2024 science
Deep Learning Is Not So Mysterious or Differentarxiv.org/abs/2503.02113
10 sats \ 0 comments \ @hn 17 Mar tech
Tversky Neural Networksgonzoml.substack.com/p/tversky-neural-networks
207 sats \ 0 comments \ @carter 21 Aug AI