A chip that can do nothing but low-precision dense linear algebra is enough for machine learning, even though it cannot run Chrome.

Added to korrents 30 Jul 2026 · How quotes work · Something wrong? Tell us

Related korrents

Our reading — they may agree, disagree or merely touch the same thing. Closest first: a shared subject counts for most, then how near the wording is.

• Falling back to older 7-nanometre chips would not rescue AI compute, because the real gap between chip generations is twentyfold, not the threefold the flops suggest. DPDylan Patel13 Mar 2026similar wording
• Inference, not training, is now the constraint, and specialized low-energy hardware will beat general-purpose GPUs and TPUs on latency. JDJeff Dean30 Jul 2026similar wording
• Machine learning is a shallow field compared with mathematics: even its most important ideas can be explained in a couple of minutes. RGRyan Greenblatt11 Aug 2026similar wording
• You cannot build a successful AI chip without first writing a competitive machine learning framework — that, not the silicon, is why Google's TPU is the only one that worked. GHGeorge Hotz29 Jun 2023similar wording
• Anyone who cannot write a full software stack for NVIDIA's generic GPUs has no chance of writing one for their own, more specialised, AI chip. GHGeorge Hotz29 Jun 2023similar wording

On the map

Open the map on its own page →