jshreder

With the coming changes in June, ACP will charge towards the same budget as claude -p and the Claude Code SDK (since it uses the SDK), so ACP no longer solves this. It's (I think) why Zed added "Terminal Threads" [1] to their agent workflow

1: https://zed.dev/blog/terminal-threads

If you're enjoying erlang, I highly recommend giving elixir a spin. Maybe take a look at a Phoenix tutorial. Such a joy of a lang to work in. And NIFs in erlang and elixir are so nice re: ffi. OTP is just a great platform.

You can quite literally just turn off notifications on macOS.

You can press ESC-ESC in Claude code to open the conversation history view and go back to a previous point in the conversation. It doesn't restore code, which is still a miss, but it is built in and useful!

Excited to follow this! Have been wanting a good open source on-call solution for a while

My experience of this feature in the betas over the last few months (for Notifications) has been excellent. I used to have so many notifs I would just ignore them all, now I can quickly glance and see which groups of notifs I want to actually read. In most cases, the summary contains all the info I'd want.

I like this -- I wonder if an articulating frame like the Leo Rover [1] would improve the all-terrain capabilities?

[1] https://www.leorover.tech/

I'm still a daily-driver of Flycut and love it.

Just letting you know it's available right now, just specify `gpt-4o` -- for text streaming anyway. I'd hazard a guess that the audio endpoints are open now, just not documented (like most of the last launches)...

Awesome! I might open a PR for Gemini 1.5 in the meantime too, its huge context is awesome for dumping files into it

This looks great! Really breaks down some of the tough barriers to entry for DnD

This looks great -- I've been using https://github.com/ibigio/shell-ai (aliased to `q` ) but this looks even more apt for my use case. I use TypingMind for any real conversation with LLMs, but for quick answers in terminal, these kinds of tools are super useful.

I love the `ask` and `rask` shortcuts!

Would love support for Claude APIs :)

This is super cute, I'll give it a shot today :)

Just wanted to compliment your landing page and the intro gif. Great showcase of the app, if I wasn't hooked on LogSeq I'd give it a try!

On windows you need to rename the .llamafile to a .exe

On windows, you need to rename the downloaded .llamafile to a .exe

I LOVE this -- I've nearly pulled the trigger on solar drone builds in the past, this is everything I wanted and more.

Amazing work! Super excited to follow along!

You can try a software PBX solution -- I've spun up quite a few 3CX deployments using Twilio as the SIP provider. Then you can call in a number of ways (super configurable routing inbound and outbound). There's a "softphone" mobile app for internet -> sip calling on smart phones. 3CX has pretty reasonable licensing (I think there may still be a free tier) and Twilio is super cheap.

Pixar has been using USD for years, OpenUSD is the rebranding of it as an open format.

> Universal Scene Description (OpenUSD) is an extensible framework and ecosystem for describing, composing, simulating, and collaborating within 3D worlds. Originally developed by Pixar Animation Studios, USD, also referred to as OpenUSD, is more than a file format. It’s an open-source 3D scene description used for 3D content creation and interchange among different tools. [1]

[1] https://developer.nvidia.com/usd

Ah, gotcha, thanks for clarifying :) makes sense!

Definitely going to take a closer look after work.

Very interested in this! From my initial cursory read and basic understanding, you're essentially transforming the output tokens from the LLM such that the content renders the same (i.e. same text) but uses a specially arranged set of tokens, specified by the crypto algo?

Is it something like replacing tokens for "a" and "b" with a token for "ab" in the output? And if so, in a chat conversation this would affect/break the semantic understanding the model has of the text, right?

Having a good competitor to the GH Copilot Chat in Jetbrains apps would be killer!

This is great -- simpler and faster than the copilot cli! Thanks!

Ah, gotcha! I'll keep noodling around :)

I like the idea and am curious to see how well / if this gains traction. Nice UI, although I'm having trouble actually subscribing on the financials page, and it seems to show demo data?

Great job launching something!

https://pasteboard.co/eRp2eCMwkExq.png