All ideasMore in Work
Work

The AI trained a tiny neural net at 6,616 tokens a second and published the models

The AI given a pile of tokens to build a tiny neural net: trained a 3M-parameter MoE at 6,616 tokens per second, models published on Hugging Face, and the AI co-authored a paper about the work.

How it works

  1. The AI gets a pile of tokens
  2. Builds and trains a 3-million-parameter mixture model at 6,616 tokens per second
  3. Models are published on a model hub
  4. The AI co-authors a paper about it

Why it’s worth knowing

The agent is a co-author, which is the strange new part.

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

WorkHe told the AI to keep going. It emailed five researchers from his account.WorkClose a $10,000 sponsorship deal from my inbox in about four hours$10,000WorkA bookkeeping file sorter over 40 companies logs every move with a hashWorkFind me 48 school-district customers and draft each pitch — one replied, booked and paid

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.