Achille Lacoin 2025-06-02 20:47:33 Ok last screenshot and I'll stop spamming about my project, this is just sooo fun (and a new spin on the classic "summarize this post" demo)
Tom Lieber 2025-06-03 02:35:36 Don’t stop until the rate limiter kicks in. This project is rad.
Mariano Guerra 2025-06-03 12:53:28 Marek Rogalski 2025-06-04 06:28:55 This is the first time I've seen an LLM just do it's job quietly. No "here you go" at the end of a complex task makes it feel so much more professional.
Scott 2025-06-03 14:57:18 LLM-powered Method Resolution with Synonllm - I've been experimenting a lot with what new things LLMs have to offer more dynamic languages like Ruby. I'm really hooked on this idea of creating a DSL without an explicit interface, and letting users just call methods semantically and letting the LLM figure it out.
You can see kind of what I mean near the end of the video with the FileHandler class example. In that class the method names are much too long for anyone to really want to type, but that extra detail (combined with the arguments) allows the user to use the interface they'd like and have it just work. Also effectively creating method overloading / dynamic argument-based dispatch in Ruby with the help of an LLM...
Marek Rogalski 2025-06-04 06:35:04 This is how every compiler should be handling the "no such function" case from now on.
Lu Wilson 2025-06-08 14:54:20 JAMMING TOGETHER
FAR APART
pastagang.cc/paper
This is a paper about live programming, written by many many many people collaborating together in one shared document, with no one credited by name. It's getting submitted tomorrow.
Ivan Reese 2025-06-08 15:07:52 Would love to see some sort of anonymized fast replay of the paper being written, with the text colored to indicate which author last touched it. I can imagine coming up with cute nicknames like "the ranter" for someone who bled out entire paragraphs in a go, or "the nitpicker" for someone who hopped around making micro wording changes, or "the poet" for someone who mostly fine-tuned word choice.
Ivan Reese 2025-06-08 15:10:32 Love the juxtaposition of this is an essay written collaboratively with no central decision-making, it's an emergent mass practice and here are my personal reflections — "I first discovered pastagang…
Lu Wilson 2025-06-08 15:29:30 most edits were completely anonymous with no way of telling who is who, sessions weren't kept or tracked. if i had to guess i would say it was around 30 people but i might be way off in either direction
Ivan Reese 2025-06-08 15:32:19 Right. I'm interested in preserving the anonymous / collective / collaborative nature of it, while finding a way to surface characters. Organisms are made of cells; what are the cells of a pastagang?
Ivan Reese 2025-06-08 15:33:51 (I don't see this as 1-to-1 with people, so my idea probably doesn't satisfy. What I'm curious about is: what were the different writing approaches that emerged, not who did them)
Lu Wilson 2025-06-08 16:03:09 it's a common thing to want to derive people or characters from the group, though i would advise letting go of that if i were you
Ivan Reese 2025-06-08 17:00:52 Tell me more! Why? I'm interested not in identifying people, but approaches (which almost certainly don't map 1-to-1 with people)
Lu Wilson 2025-06-08 18:14:19 well partly because i see it as clinging onto a non-jam-style approach - trying to focus on individuals rather than the collective but also it doesn't really matter you can do anything you want
Ivan Reese 2025-06-08 18:37:45 I was about to say "makes sense; I don't like jamming" but on second thought I do, it's just that there's lots of kinds of jamming.
