Hacker News: mark_l_watson

New comment by mark_l_watson in "How to disable or avoid intrusive AI"

mark_l_watson — Mon, 17 Aug 2026 22:32:36 +0000

You make a reasonable argument. I will take my chances and more people I talk with now seem more concerned about privacy.

New comment by mark_l_watson in "Rhombus 1.1 is now available"

mark_l_watson — Mon, 17 Aug 2026 16:29:57 +0000

That is a really good question. My personal intuition is that LLMs do well with any language as long as you set up for fast syntax checking tools, access to either a REPL or very fast to run tests, etc.

I usually use small local models, and the work to set up very concise skills and efficient tooling is a big part of the fun. I have also adopted the practice of writing my own custom coding harnesses (these can be less than 2000 lines of code, not the huge project you might expect.)

New comment by mark_l_watson in "Rhombus 1.1 is now available"

mark_l_watson — Mon, 17 Aug 2026 16:24:25 +0000

Since 1982 I have spent much of the time being paid to work in Lisp languages.

A weird thing: whichever Lisp language I am currently using for work (or a side project) is my favorite.

New comment by mark_l_watson in "Rhombus 1.1 is now available"

mark_l_watson — Mon, 17 Aug 2026 16:18:43 +0000

I love Racket, and have a ton of Racket code I have written over the years. When I get home from a vacation I will have an AI translate a small sample of my Racket code to Rhombus: easiest way for me to play with the language.

New comment by mark_l_watson in "How to disable or avoid intrusive AI"

mark_l_watson — Mon, 17 Aug 2026 16:01:03 +0000

Good list! Removing as much as possible all AI and surveillance features, then carefully adding back the very few I want is the way I roll.

New comment by mark_l_watson in "How to disable or avoid intrusive AI"

mark_l_watson — Mon, 17 Aug 2026 15:58:14 +0000

On our car I can hook up my iPhone via Bluetooth to listen to audio books and music, bypassing carplay.

New comment by mark_l_watson in "Health benefits of Tai Chi"

mark_l_watson — Sun, 16 Aug 2026 13:19:22 +0000

There are a near infinite number of Qi Gong and Tai Chi videos on YouTube. I prefer to following new videos, and where my wife and I live they have Tai Chi and Yoga classes. A great use of time, and the feeling good benefits are manefest.

New comment by mark_l_watson in "Why Target Common Lisp for Code Generation?"

mark_l_watson — Thu, 13 Aug 2026 03:22:09 +0000

In the mid 1980s I wrote a commercial neural network product SAIC Ansim and I usually got things working in Common Lisp first, then manually translated to C++. Now we can write in CL and use coding agents to translate to other languages... progress!!

New comment by mark_l_watson in "Hax – a minimalist, terminal-native coding agent written in C"

mark_l_watson — Thu, 13 Aug 2026 01:49:55 +0000

I didn't try Hax but I hope someone who has can answer a question: does it support suspending current operation if user hits ESC key?

EDIT: I just looked at interrupt.c in the github repo: handles user interrupts. I trashed my Common Lisp harness because I had problems handling interrupts in a portable way. I did better with Racket. I am traveling on vacation without a computer, will try Hax when I get home.

New comment by mark_l_watson in "Pixel 11 Pro Fold"

mark_l_watson — Wed, 12 Aug 2026 16:14:45 +0000

I am only 75, but in a few years I have thought of downsizing to one device (and a VPS for a little coding). A future version of this phone that is triple fold would work for me.

New comment by mark_l_watson in "Jolt: Clojure compiler implemented with Chez Scheme"

mark_l_watson — Tue, 11 Aug 2026 22:34:14 +0000

Thanks for the kind words.

I just built the Chess example in my Clojure book and the executable was a tiny 18M.

New comment by mark_l_watson in "Jolt: Clojure compiler implemented with Chez Scheme"

mark_l_watson — Tue, 11 Aug 2026 22:26:05 +0000

Great work. It just simply worked for me.

New comment by mark_l_watson in "Nvidia Nemotron 3.5 Lightning and NeMo Switchyard"

mark_l_watson — Tue, 11 Aug 2026 22:15:49 +0000

I love the wave of new small model releases. Pleasantly surprising that an NVIDIA model runs so well on Apple Silicon using MLX! I was using nemotron-3.5-lightning:30b-mlx with OpenCode on my old (cheap) Mac this morning and no bad experiences except for running slowly.

New comment by mark_l_watson in "Squeak 6.1"

mark_l_watson — Tue, 11 Aug 2026 11:48:23 +0000

I used to love using Squeak but moved to Pharo to get better high resolution display support. I should try the Squeak 6.1 release.

New comment by mark_l_watson in "Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows"

mark_l_watson — Tue, 11 Aug 2026 10:15:55 +0000

From the Ollama docs for this new model:

Ollama's MLX engine provides state-of-the-art performance on Apple Silicon, with support for DFlash and image input:

ollama run muse-glimmer:30b-mlx

New comment by mark_l_watson in "Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows"

mark_l_watson — Mon, 10 Aug 2026 16:22:04 +0000

To be honest, I never give benchmarks a look. I just use the models for whatever I need to work on, so I can't really make comparisons that are useful for other people.

New comment by mark_l_watson in "Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows"

mark_l_watson — Mon, 10 Aug 2026 15:06:34 +0000

Meta is rocking AI. As of last week I have been using their excellent muse coding harness with their model Muse Spark 1.2.

Starting this morning I am running their new local 30B model muse-glimmer on my old MacMini 32G using Ollama (remember to increase the context size!) and pi coding harness. I am getting good results with muse-glimmer running locally, with the caveat that everything runs slowly (e.g., give it a task and then go walk outside or do Qi Gong exercises for a while).

New comment by mark_l_watson in "Mea Culpa – Dark Hours"

mark_l_watson — Sun, 09 Aug 2026 18:29:32 +0000

He did the right thing. The very idea of Claude copying an existing project to answer one of my prompts or a whole project in Claude Code is a nightmare scenario.

I have all but given up using the multiple trillion weight models in favor of smaller open weight models that have hopefully abstracted away copyrightable details. Right now deepseek-v4-flash-0731 seems usually perfect for my needs.

I saw Cees de Groot post about LLM vibe coded projects containing all sorts of licensed material, and I think he is correct.

Perhaps another good reason to just use the AGPL for new projects? I decided to use the AGPL for may latest fun project https://github.com/mark-watson/racket-coding-agent (personal AI coding harness written for my own use in Racket Scheme). Everything I do is open source or open content books, so I am happy to have everything I do to be used by humans and also for AI training, however: it is scary to by mistake be in the position of not acknowledging other work when appropriate.

New comment by mark_l_watson in "Ask HN: What are you working on? (August 2026)"

mark_l_watson — Sun, 09 Aug 2026 18:08:51 +0000

I am retired, so this may not be of general interest: I am working on my fourth AI coding agent, this one written in Racket Scheme: https://github.com/mark-watson/racket-coding-agent

I don't necessarily suggest that anyone besides myself use it. I open-sourced it to perhaps give other people ideas, but it is tailored to just my own needs (e.g., hardwired to use deepseek-v4-flash-0731 via FireWorks.ai; supports just the tools I need).

New comment by mark_l_watson in "Jolt: A Clojure compiler implemented on top of Chez Scheme"

mark_l_watson — Sat, 08 Aug 2026 17:55:03 +0000

Are you one of the authors?

Great job! It took me just a few minutes to install Jolt and build a native executable for the Chess program in my Clojure book. Jolt rocks!!!