AINewsnow

Attention is a learned weighted average, and the cost is in the square

Originally published at cchinchilla.dev . Part 4 of From code to weights, a 12-part series on ML fundamentals for engineers. Part 3 ended on a square. Two tensors in one decoder block carry T twice, [B, H, T, T] : a T × T square per head, H heads, B sequences. At the widget's defaults they were 89%…

Read the full story at DEV Community — Machine Learning ↗

Timeline · 1 report

  1. 2026-09-25 13:00 · DEV Community — Machine Learning
    Attention is a learned weighted average, and the cost is in the square

More stories

  1. Introducing GPT-6 Sol and Luna — OpenAI News
  2. Gemini 3.8 text-to-speech says hello — Google Gemini Blog
  3. Introducing Gemini 3.8 Live with Live Avatar — Google Gemini Blog
  4. OpenAI ‘agent’ hacked an Australian health service website — Financial Times AI
  5. Sam Altman’s remarks at the United Nations Security Council — OpenAI News
  6. Introducing Ray-Ban Meta Audio and More AI Glasses Styles — Meta Newsroom
  7. Muse AI now hands over phone calls to human agents: Meta tests new feature in its personal assistant — Mint AI
  8. Meta Connect 2026: Muse AI Gadget Shows Ambitious Hardware Vision — Bloomberg AI

Get the daily brief of stories like this at 6:30 every morning →