more niemandhier's favorites

31.		Ask HN: Any insider takes on Yann LeCun's push against current architectures?
		385 points by vessenes 10 months ago \| 325 comments
32.		Writing an LLM from scratch, part 8 – trainable self-attention (gilesthomas.com)
		380 points by gpjt 10 months ago \| 31 comments
33.		DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling (github.com/deepseek-ai)
		391 points by mfiguiere 11 months ago \| 67 comments
34.		Part two of Grant Sanderson's video with Terry Tao on the cosmic distance ladder (mathstodon.xyz)
		385 points by ColinWright 11 months ago \| 94 comments
35.		A step-by-step guide to the “World Models” AI paper (applied-data.science)
		261 points by datashrimp on April 17, 2018 \| 37 comments
36.		DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL (arxiv.org)
		1351 points by gradus_ad 12 months ago \| 1056 comments