Sam Carlton

@benln Happy to host one in Tulsa. We’ve got people super hungry for more of this

Cafe Cursor has hit 75 cities in 2026 (so far!) Want to host one in your city? Reach out.

@alexalbert__ Hey, I’m curious if there’s anyway way to push along a Ambassador application for Tulsa. I’ve been getting a flood of people that have been looking for a community to talk about Claude Code in and we’ve already got the infrastructure of Techlahoma.

Support Walter White

@Hesamation @lindavivah @robertnishihara @robertnishihara I’m sure there are reasons why this is almost impossible but I’m curious what the bottlenecks actually are. Would it even be possible to get a good reply to a single message with downloading GBs of layers?

@Hesamation @lindavivah @robertnishihara @robertnishihara Great breakdown! Working in Web Dev I’ve always suspected you might be able to eventually shard some aspect, like expert layers, across like sqlite-http vfs to be able to stream only the parts of the model you need but I just don’t know enough llms

bro casually walks and explains 5 GPU performance optimization methods for LLMs. one of the most simple and intuitive explanations for beginners.

Also you can try making it work yourself. The code is completely open source and you can see all the details of how it works here: github.com/ThatGuySam/emo…

This means our emoji search can match emojis to words it's never seen before. No exact match required. It's not perfect, in fact, at the time of writing, it crashes a lot on mobile but it's a lot of progress for the constraints we're working under.

Have you ever gotten frustrated searching for the right emoji? You know you've seen the emoji but you don't know the exact name. Most search even on iOS using simple text matching: 🧵