Hacker News: lordmathis

New comment by lordmathis in "So where are all the AI apps?"

lordmathis — Tue, 24 Mar 2026 15:33:51 +0000

I also experienced this with my personal projects. It was really easy to just workshop a new feature. I'd talk to claude and get a nice looking implementation spec. Then I'd pass it on to a coding agent which would get 80% there but the last 20% would actually take lot more time. In the meantime I'd workshop more and more features leading to an evergrowing backlog and an anxiety that an agent should be doing something otherwise I'm wasting time. I brought this completely on myself. I'm not building a business, nothing would happen if I just didn't implement another feature.

Show HN: Llamactl – Self-hosted LLM manager with OpenAI-compatible routing

lordmathis — Tue, 17 Mar 2026 15:47:13 +0000

Llamactl is a unified management system for running local LLMs across llama.cpp, MLX, and vLLM backends, with a web dashboard and OpenAI-compatible API.

I originally built this because I got tired of constantly SSHing to my server to edit a config just try out a new model. It's grown a lot since then.

What it does:

Web UI for creating and managing LLM instances from your browser

Full llama.cpp model lifecycle - download from HuggingFace, create preset.ini configs with an in-browser editor, load/unload models via router mode

Automatic idle timeout, LRU eviction, and instance limits

llama.cpp, mlx_lm and vllm backends

OpenAI and Anthropic API compatible endpoints (backend-dependent)

Multi-node support for distributing instances across hosts

Inference API keys with per-instance access control

docs: https://llamactl.org/stable/

Comments URL: https://news.ycombinator.com/item?id=47414320

Points: 2

# Comments: 0

New comment by lordmathis in "My Journey to a reliable and enjoyable locally hosted voice assistant (2025)"

lordmathis — Mon, 16 Mar 2026 15:40:54 +0000

I started designing and building a voice assistant for myself and then realized that the only time I'd find it useful would be during cooking to set timers. But a loud extractor fan would be running making the voice recognition very difficult.

New comment by lordmathis in "Yann LeCun raises $1B to build AI that understands the physical world"

lordmathis — Tue, 10 Mar 2026 20:12:27 +0000

Sure, Claude and other SOTA LLMs do generate about 90% of my code but I feel like we are not closer to solving the last 10% than we were a year ago in the days of Claude 3.7. It can pretty reliably get 90% there and then I can either keep prompting it to get the rest done or just do it manually which is quite often faster.

New comment by lordmathis in "Show HN: How I topped the HuggingFace open LLM leaderboard on two gaming GPUs"

lordmathis — Tue, 10 Mar 2026 16:27:01 +0000

That's cool. I tried the b64 thing on my local qwen3.5 27b without access to tools and it did it.

New comment by lordmathis in "Yann LeCun's AI startup raises $1B in Europe's largest ever seed round"

lordmathis — Tue, 10 Mar 2026 15:35:50 +0000

It's 6 months away the same way coding is apparently "solved" now.

New comment by lordmathis in "A postmortem of three recent issues"

lordmathis — Thu, 18 Sep 2025 11:43:58 +0000

I learned to write well testable code when I learned go. It pushes you to pass interfaces instead of direct implementations. There's also no inheritance, just composition. While there's no 1 to 1 translation to Python the concepts are still useful. It can be easier in Python thanks to duck typing.