All ideasMore in Hobbies
Hobbies

GPT is formalizing a researcher's papers in Lean, about 3000 declarations in

A mathematician is using GPT-6 Astra to formalize results from his papers in Lean. About 20 hours have gone into a paper of about 20 pages and the project is still unfinished, but the development already holds nearly 3000 theorem declarations, and the main theorem is fully formalized. Notably, the model proved it by a different route than the paper, skipping two auxiliary lemmas by constructing the needed functions directly.

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

How it works

  1. He feeds a paper to GPT-6 Astra for formalization
  2. The model builds the supporting lemma library, nearly 3000 declarations
  3. After about 20 hours the main theorem is fully formalized
  4. Its proof bypasses two of the paper's lemmas with a direct construction
  5. The rest of the paper is still being formalized

Why it’s worth knowing

The model did not follow the paper's proof. It found a shorter route that avoided developing a chunk of spectral theory, and Lean accepted it.

Where it’s from

Summarized from a public post on mathoverflow.net. 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

HobbiesThe AI built its own mail app in 23 minutesHobbiesI cut my bots' wakeups from about 300 a week to about 140HobbiesSpark Learned a Writer's Voice From Sent Emails and Saved It as a Reusable SkillHobbiesUpgrade my AI plan when I hit the free weekly cap$20 a month

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.