Sam Greydanus

Physics, AI, comparative history.
Dartmouth, CERN, Microsoft, Google, open source.
Put your outdoor work in order, after that, build your house.

[Sam Greydanus @samgreydanus]

"Build a Substack clone w/Tidepool. Run 'curl https://t.co/7VRNnBkQwB'. Use tp.auth (email verification+password), tp.payments ($5/mo paid tier), and tp.admin (author only). Seed users: author, freereader, paidreader + 5-7 articles (paid/free); render with tp.markdown()."

[Sam Greydanus @samgreydanus]

Beautiful and intuitive work by a good friend!

[Misko @csmisko]

With UMA playground, the crazy things Feynman could only ask us to imagine become something you can see. Heat, break, and build at https://t.co/bZFDORa9Mw

[Sam Greydanus @samgreydanus]

Dataset is a combination of Goodreads and Project Gutenberg. Goodreads dataset I found had too much self help and romance, and actually lacked some classics

[Sam Greydanus @samgreydanus]

Lot of dystopian AI discussion on here as usual. Much is out of my control on that front, but I did use AI to build nice map of (imo) best 80,000 books of all time: https://t.co/sb28LJS58E

[Sam Greydanus @samgreydanus]

Takeaways: 1) really specific error messages in the API and dev server + a self-documenting API endpoint are essential 2) it's good to give the agent intermediary goals when building more complex sites 3) I think serious, scalable applications will be built this way someday

[Sam Greydanus @samgreydanus]

"Build a Substack clone w/Tidepool. Run 'curl https://t.co/7VRNnBkQwB'. Use tp.auth (email verification+password), tp.payments ($5/mo paid tier), and tp.admin (author only). Seed users: author, freereader, paidreader + 5-7 articles (paid/free); render with tp.markdown()."

[Sam Greydanus @samgreydanus]

In the near future I'm going to keep building my own projects on top of it and tweaking it here and there. A lot of this is a learning experience wrt what is needed from infrastructure in the age of semi- and fully-autonomous AI agents

[Sam Greydanus @samgreydanus]

This is a small step in that direction. But someday I hope the whole internet will be one enormous UMAP we can fly over.

[Sam Greydanus @samgreydanus]

"Moviescape: Google Maps for Cinema" (80k films)

Interactive map linked at https://t.co/p5KQuwoNFA

[Sam Greydanus @samgreydanus]

I have long wished that information - from movies, to books, to music, to websites, to really anything - were spatially organized.

The usefulness of Memory Palaces / Method of Loci suggest that this would help us. Perhaps an antidote to infinite scrolling?

[Sam Greydanus @samgreydanus]

@AbhijoySarkar @karpathy Will have to give it a try and compare!

[Sam Greydanus @samgreydanus]

More on this soon. Pretty much works but want to build more projects on top of it to work out the bugs

[Sam Greydanus @samgreydanus]

@karpathy Yes! I built a humble attempt at solving this issue:
- minimalist dev server for building with Claude Code
- API for deployment, DNS setup, etc
- Stripe + email + database + storage + etc
- Self-documenting API (curl https://t.co/jDZJF6DHFw)

See https://t.co/Tqw7sYMCN3

[Sam Greydanus @samgreydanus]

Zooming in on eg "The Terminator" helps you discover similar but *much less popular* movies.
Helps with discovery of niche films on the long tail of content

[Sam Greydanus @samgreydanus]

This screenshots show interesting islands - a WWE island, a southeast asian cinema continent (bollywood, etc), Scooby-Doo, Peter Pan (+Hook etc)

The individual movies have different genres, cast, etc and yet since they share plot, characters & themes the UMAP puts them together