mrtedbear's favorites

1.		Robust autonomy emerges from self-play (arxiv.org)
		139 points by reqo 4 days ago \| 62 comments
2.		Understanding Reasoning LLMs (sebastianraschka.com)
		471 points by sebg 4 days ago \| 187 comments
3.		Pre-Trained Large Language Models Use Fourier Features for Addition (2024) (arxiv.org)
		147 points by Kye 5 days ago \| 40 comments
4.		S1: A $6 R1 competitor? (timkellogg.me)
		844 points by tkellogg 6 days ago \| 412 comments
5.		Ask HN: Do you know travel blogs that have animated SVG maps of their travels?
		193 points by trebeljahr 7 days ago \| 59 comments
6.		Andrej Karpathy: Deep Dive into LLMs Like ChatGPT [video] (youtube.com)
		574 points by leroman 5 days ago \| 46 comments
7.		Deep Reinforcement Learning: Pong from Pixels (2016) (karpathy.github.io)
		111 points by Anon84 5 days ago \| 6 comments
8.		Gemini 2.0 is now available to everyone (blog.google)
		610 points by meetpateltech 5 days ago \| 265 comments
9.		3D scene reconstruction in adverse weather conditions via Gaussian splatting (arxiv.org)
		53 points by PaulHoule 13 days ago \| 14 comments
10.		How has DeepSeek improved the Transformer architecture? (epoch.ai)
		258 points by superasn 13 days ago \| 68 comments
11.		DeepSeek's multi-head latent attention and other KV cache tricks (pyspur.dev)
		292 points by t55 13 days ago \| 72 comments
12.		The Illustrated DeepSeek-R1 (languagemodels.co)
		578 points by amrrs 14 days ago \| 118 comments
13.		Open-R1: an open reproduction of DeepSeek-R1 (huggingface.co)
		394 points by jonbaer 14 days ago \| 234 comments
14.		Run DeepSeek R1 Dynamic 1.58-bit (unsloth.ai)
		767 points by noch 14 days ago \| 332 comments
15.		DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL (arxiv.org)
		1351 points by gradus_ad 16 days ago \| 1056 comments
16.		Show HN: Making AR experiences is still painful – had to make my own editor (ordinary.space)
		161 points by boriskourt 15 days ago \| 27 comments
17.		DeepSeek releases Janus Pro, a text-to-image generator [pdf] (github.com/deepseek-ai)
		912 points by reissbaker 14 days ago \| 674 comments
18.		The impact of competition and DeepSeek on Nvidia (youtubetranscriptoptimizer.com)
		655 points by eigenvalue 16 days ago \| 479 comments
19.		Tensor Product Attention Is All You Need (arxiv.org)
		160 points by eunos 20 days ago \| 104 comments
20.		UK's hardware talent is being wasted (josef.cn)
		636 points by sebg 22 days ago \| 1131 comments
21.		NeuralSVG: An Implicit Representation for Text-to-Vector Generation (sagipolaczek.github.io)
		782 points by lnyan 33 days ago \| 72 comments
22.		Nvidia Makes Cosmos World Foundation Models Openly Available to Physical AI Devs (nvidia.com)
		6 points by magicalhippo 35 days ago \| 1 comment
23.		Spline Distance Fields (zone.dog)
		180 points by ibobev 35 days ago \| 27 comments
24.		Lfgss shutting down 16th March 2025 (day before Online Safety Act is enforced) (lfgss.com)
		798 points by buro9 56 days ago \| 545 comments
25.		A Gentle Introduction to Graph Neural Networks (2021) (distill.pub)
		362 points by misonic 53 days ago \| 33 comments
26.		Satellite powered estimation of global solar potential (research.google)
		265 points by jonbaer 53 days ago \| 204 comments
27.		Cultural Evolution of Cooperation Among LLM Agents (arxiv.org)
		246 points by Anon84 54 days ago \| 131 comments
28.		New LLM optimization technique slashes memory costs (venturebeat.com)
		445 points by hochmartinez 59 days ago \| 214 comments
29.		Geometry clipmaps: simple terrain rendering with level of detail (2017) (mikejsavage.co.uk)
		40 points by todsacerdoti 61 days ago \| 2 comments
30.		Gemini 2.0: our new AI model for the agentic era (blog.google)
		1015 points by meetpateltech 61 days ago \| 490 comments
		More