isembedded Public experiments in economic geography
Experiment 01

Write an Economic Geography Paper in 6 Days on a Remote Beach

I attempt to write one quantitative paper in six days, using AI tools and web search, without consulting a single human being about it. Every hour is streamed. The recording becomes the material for a second paper.

Day 3 of 6 · Writing · Pok Fu Lam Still processing dependent variables, related to rural innovation in the United States. Watch live
Updates

Project status—

Progress

Where the paper is.

Eighteen tasks, estimated at 36.75 hours before the week began. The bar is weighted by those estimates, so a long task moves it further than a short one, and nothing counts until it is finished. This is the board that appears on the stream.

0%

D

Normative timeline

23 Aug

Arrival

I take the ferry out to Chi Ma Wan and start recording. From that point I have no contact with my co-authors, my colleagues or anyone else in the research community until the recording stops.

23 Aug · 22:00

Kickoff stream

I open the broadcast by explaining what the paper is supposed to be and what I think is most likely to go wrong. Then I put the first question to a model on camera.

22:00Hong Kong 14:00UTC 15:00London 16:00Berlin 10:00New York 07:00Los Angeles 00:00Sydney, Mon
23 – 28 Aug
08:00 – 18:00 HKT

The writing week

I write during the day, from eight in the morning until six in the evening, Hong Kong time. The stream is unedited, so you will see the prompts I write, the answers I throw away, the dead ends I follow, and the long stretches where very little happens.

24 – 26 Aug
21:00 HKT

Nightly conversations

These are casual hangouts with colleagues and viewers about academic writing with AI, and anyone watching can ask a question while we are live. Nobody helps me with my own paper.

Mon 24TBATue 25TBAWed 26TBA
28 Aug

Departure

I leave with whatever I have managed to write. It might be a finished draft, it might be half of one, and it might be a cautionary tale. I will publish it either way.

Sep – Dec

Paper number 2: the meta paper

All three of us watch the footage on our own and then compare what we found. Two of my co-authors take no part in the writing week, so their reading acts as a check on my account of my own process.

2027

Publication?

Stay tuned to find out.

The stakes

Livestream challenges are supposed to have stakes.

Can I write an academic paper that survives desk rejection at a Scopus-indexed journal?

A man grinning over a plate of lamb chops at a restaurant table, Hong Kong harbour lit up behind him. If it works

The masalewali chaanp at New Punjab Club.

Lamb chops, marinated twice over 48 hours, in Central. Eaten alone, on camera, with no one to split the bill with.

A man at a cluttered desk late at night reading a manuscript, surrounded by economic geography books and notebooks. If it doesn't

24 additional hours of service to the economic geography community.

Reviewing, letters, discussant duty — whatever is asked, until the hours are paid. Also livestreamed, in full.