News for hackers. Stuff that matters.

tritondev

Re:Ask HN: What's your current AI agentic setup? on Thursday November 05, 2026 @02:36AM (#50376262)
I built a Qt GUI-based harness, Humbug, that runs on MacOS, Linux, and Windows (I have reasons to use all 3). Has only 3 runtime dependencies other than the Python standard library: https://github.com/m6r-ai/humbug

Usually have 3 or 4 instances running at a time and lets me use LLMs from 9 different providers (and not using their libraries either). The low dependency approach was slightly limiting early on but now makes it very easy to extend and makes it very easy for an LLM to integrate new features or optimize existing ones.

I typically use Claude Sonnet for document-related tasks, and currently DeepSeek 4.1 Flash is my current go to for coding (it's insanely cheap on ollama.com) and I find it's still fast and reliable at very large context lengths. Previously I used GLM 5.2 a lot and before that was Sonnet for most things.

Humbug lets one AI delegate tasks to another and it can choose different models/providers when it does, so works nicely for getting second opinions on things. I haven't yet found a need for an agent swarm though - more often the parallelism comes from working on multiple projects at the same time.

One of the biggest unlocks for me in the last few months is having AIs write ADRs to capture design thinking as a project progresses. It lets new AI sessions discover the intent behind the current work and surface any potential conflicts that might arise with new requests.

One fun feature is the AI can control pretty-much any UI surface the user can control too, and it's quite fun to watch it edit files (you can watch it scrolling around the file in an editor) or use a terminal. It's a nice visual way to see what's going on.

Re:Mouse: Precision Editing Tools for AI Coding Agents on Sunday July 05, 2026 @12:22PM (#48795461)
I decided to build a pure functional, open-source, programming language (Lisp-inspired) to help my dev tools do complex editing.

The idea is the AI writes a functional transform for a file or editor buffer of whatever form it needs.

Brief LinkedIn note with an example: https://www.linkedin.com/posts/davejh_its-a-great-feeling-wh...

Re:Show HN: Building an open-source agentic terminal on Monday September 15, 2025 @01:36PM (#45252603)
The project has 65k lines of code (plus another 11k of tests and tools), but a lot of the heavy lifting was done by LLMs with me providing them detailed problem statements, reviewing their work, and then having them fix/improve what they'd done. At this point I'd guess LLMs have built about 80%-85% of the code and I've built the rest. I've had to keep the architecture clean, however, because the LLMs have struggled with that.

I built the Metaphor prompting framework first, then worked my way up from there.

The project has been running for about a year, and I probably averaged about 40 hours a week, so something like 2000 hours so far.

Re:AI models need a virtual machine on Sunday August 31, 2025 @11:06AM (#45083736)
The concept that LLMs will need to have strong isolation and that this is done with the same sort of diligence normally applied to virtual machine design makes a ton of sense. It's exactly the same reason we enforce such behaviours in operating systems.

I took a first pass at enumerating some ideas a few weeks ago: https://davehudson.io/blog/2025-08-11

My thought was to try and define this in a slightly more concrete way by thinking about analogies between the way LLMs operate and more conventional OS processes/tasks.

Building some of the core abstractions isn't too hard - I already have one that unifies the chat and tool use interfaces for 8 different LLM backends. That lets tool approvals be managed in a centralized way. I've not yet implemented a capabilities model but it feels natural, and I worked with one back in the 90s (VSTa if anyone is interested in historical OSes). A key part will be to allow one LLM to delegate a subset of its current capabilities to another (I already built the delegation tooling)

Show HN: Metaphor, an LLM Prompting Language

https://github.com/m6r-ai/getting-started-with-metaphor

For the last 6 months I've been building and using an open-source structured LLM prompting language called Metaphor. It has a prompt compiler that lets you use a modular approach to constructing LLM problems, rather like a normal programming language.I, and some early adopters, have been using this for doing things like complex software design and document generation work. It's sort of the...

( Read More... | no comments | on HN )

Show HN: Humbug and Metaphor – tools for building with AI

https://github.com/m6r-ai/humbug

A while ago I posted a link to an earlier version of this, but a lot has changed since then!Humbug is a GUI designed to let you do more structured software engineering with AI. Most of the development work has been driven using Metaphor, a very simple natural-language based format for capturing detailed context.Metaphor aims to make development prompting much more repeatable and to offset many...

( Read More... | no comments | on HN )
I'll put one out :-)
Definitely not a VSCode fork - it's written in Python for one thing :-) In fact it has very few package dependencies other than the standard python libs - just PySide6 and qasync to allow me to use the Qt widget set, and aiohttp to implement the client side of the REST interfaces to the AI backends. The only other dependency is on the m6rclib I wrote a few months ago - that's a prompt compiler engine and that has no dependencies either.

The "coded by AI" is because the AI did the bulk of the code generation leaving me to focus on the design, improving the structure, etc. There are a few places where I did more of the design work (e.g. the structure of the parsers and lexers used for syntax highlighting), but I had the AI do much of the refactoring.

To keep the AI on track I designed a lightweight language, Metaphor, that keeps it focused on the intent of what I want. There are currently about 1300 lines of Metaphor, describing the user-visible behaviour of a 15k lines of Python app.

Of course, I watch the AI pretty carefully to ensure it doesn't do weird things but give it the right context and it's pretty amazing to watch (there's a video of me having the AI build the JSON lexer/parser yesterday morning up on YouTube: https://www.youtube.com/watch?v=E-1XbJkHwHQ). For transparency, I did find one bug in the 300 lines it coded in the video :-)