xmstan
Re:Ask HN: What are you working on? (August 2026)
on Monday August 10, 2026 @06:41AM (#49241936)
I am working on Bonsai - an open-source conversational framework for brand-safe assistants and agents. It works with text and voice based channels. For example we recently built an email agent that qualifies leads and sends pdf offers back. 2 years ago (before open-sourcing) we built an AI podcaster that conducted interviews in a physical space.
GH: https://github.com/utter-one/bonsai
Re:Why current LLM costs are not sustainable
on Friday June 26, 2026 @04:51AM (#48684121)
There is a good and cheap alternative: R9700 32GB + Qwen 3.5 27B
Won't give you SOTA performance, but will be as good as Sonnet a few months back.
Re:Someone Build a OS for Claude Code
on Sunday June 21, 2026 @03:09PM (#48621675)
>If Claude Code can install packages, write and run code, manage files, browse the internet, and operate your entire machine — what do you need a desktop for?
Why would you need a dedicated OS for that? Especially if you can run it on an OS that is properly supported with updates, packages and so on...
Re:Anthropic to Require ID Verification for Certain Capabilities Start...
on Sunday June 21, 2026 @08:49AM (#48618482)
Funny how no-one talks about AI neutrality like we used to discuss net neutrality. We literally now enter a space where not only you will have to prove your identity with a gov issued ID, but they will silently block you if they deem you try to use it in a way that they don't like.
It is literally similar to a situation where your ISP would investigate all sites you visit and limit your bandwidth if they don't like the the ones you enter...
Re:Ask HN: Has anyone replaced Claude/GPT with a local model for daily...
on Tuesday June 16, 2026 @05:08AM (#48552563)
Yes, we use Qwen 3.6 27B Q6_K. We use it on Radeon R9700 32GB and it delivers 50tps with MTP. We compare it to Sonnet from 4-6 months ago when it comes to output. Totally usable for daily coding.