All ideasMore in Work

His kernel-tuning agent loop fixes the numbers and has not yet hit the speed target

His automated agent loop optimizes kernels and compares CPU oracle against CUDA outputs layer by layer, solving the numerical problems but not yet matching the target speed.

This only partly worked. Read what happened before you try it.

How it works

  1. An automated agent loop optimizes kernels
  2. Compares the reference implementation's outputs against the GPU outputs layer by layer
  3. Solves the numerical problems
  4. Has not yet matched the target speed

Why it’s worth knowing

Right but slow is a real stopping point, and he reports it as one.

Where it’s from

Summarized from a public post on news.ycombinator.com. See the original ↗

Upgraded prompt

A ready-to-use prompt for this idea, built from research on what makes AI agents do the job right: who the AI should be, the exact steps, and a check to make sure it was done the way you wanted.

1Who the AI should be
2The prompt, with the steps
3The check when it’s done
Upgraded prompts are coming soon.

Try next

Every idea is a real post from someone who tried it, summarized in our words, with a link to the original. App names are swapped for plain words.