All ideasMore in Hobbies
Hobbies

Whisper and an LLM rebuilt a 1973 lecture blackboard from tape audio

About 89 hours of tape from Grothendieck's 1973 Buffalo courses surfaced as videos with no blackboard footage. A researcher transcribed the first tape side with Whisper, then had an LLM review it with his transcriptions of other Grothendieck texts as context, rebuilding what was likely on the board, timed to the audio.

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

How it works

  1. He transcribes the tape with Whisper
  2. He gives an LLM his transcriptions of the lecturer's other working notes as context
  3. The LLM reviews the transcript against that context
  4. He checks items by hand and against Lean
  5. The board for the first tape side is rebuilt

Why it’s worth knowing

The board work was never recorded anywhere. Feeding the model the lecturer's own other writings let it reconstruct notation that audio alone does not contain.

Where it’s from

Summarized from a public post on hsm.stackexchange.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

HobbiesSpark Learned a Writer's Voice From Sent Emails and Saved It as a Reusable SkillHobbiesMy agent is counting all 77,000 stories in my Instagram story archiveHobbiesFill and submit UK master’s applications from one master fileHobbiesMy smart ring sends voice notes to the AI, and the AI sorts my day

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.