Tell me about it!

I'm curious. How does this coordination work? Do you have any notes that I can refer to?

Just tell Claude to create tmux sessions for each, it can figure out the rest.

Nice work. Under "MCP" section, "Local" shouldn't be prepended with "~". It should just be `.claude.json (per project)`

Thanks, fixed.

I worked for a client who was all about scrolljacking. Then he discovered parallax effect, and there was no looking back. He fired me, and got another team who didn't have any opinions.

Now the page stutters on every device other than iPhone 16+ with 5G. :shrug:

It will be nice to know how many legal personnel fell for this trip. Maybe a leaderboard :D

If AI agents need CLIs, then whats stopping them from using APIs directly. I see CLIs as good wrappers over APIs, and nothing more. What more will CLIs provide which `curl -X POST` can't/won't provide?

Context limits and context poison/rot/whatnot stops them. CLI's are a great way to make a focused context. But any other trick to filter out noise would also work.

Off topic: Back in the day, C++ programming books Andrei Alexandrescu are a joy to read, especially, Modern C++ design.

Also, this presentation https://accu.org/conf-docs/PDFs_2007/Alexandrescu-Choose_You... killed a lot of bike shedding!

Congratulations on open sourcing this. Is there a small video explaining how it feels?

Thank you!

Posted this morning an overview of the project: https://x.com/NathanFlurry/status/2018366627021291699

> Small models have gotten remarkably good. 1 to 8 billion parameters, tuned for specific tasks

What models is Mozilla talking about?

Firefox does offline translation and offline tts. It is quite amazing. Unfortunately half the tech crowd is like "BURN anything that has been in the same room as AI" and the other half is yoloing agentic browsers and uploading all their pron history to the datalakes