Hacker News: mark_l_watson

New comment by mark_l_watson in "Tofolli gates are all you need"

mark_l_watson — Sun, 12 Apr 2026 12:54:32 +0000

That sounds interesting. I just checked out the examples in the Haskell Janus implementation: https://github.com/mbudde/jana

New comment by mark_l_watson in "I've sold out"

mark_l_watson — Thu, 09 Apr 2026 10:41:36 +0000

looks nice!

New comment by mark_l_watson in "Muse Spark: Scaling towards personal superintelligence"

mark_l_watson — Wed, 08 Apr 2026 20:37:15 +0000

That would be my question also. I like it when companies have easy to sign up for, pay as you go models. Being able to buy $5 worth of tokens and get an API key - in less than a few minutes - is ideal.

New comment by mark_l_watson in "I've sold out"

mark_l_watson — Wed, 08 Apr 2026 13:59:15 +0000

What you are suggesting might sound difficult to some people, it is possible: in the last week I co-wrote (with Antigravity with Claude as the backend) an Emacs package for agentic coding that also just uses ‘rg’ for finding relevant code for the context, call out to a model, and handle creating a diff with merging tools. I love using my own code that provides inside Emacs vibe coding and I would suggest others try building the same thing.

EDIT: here is a link of what I wrote just for my own use: https://github.com/mark-watson/coding-agent

New comment by mark_l_watson in "I've sold out"

mark_l_watson — Wed, 08 Apr 2026 13:46:39 +0000

Pi does seem special, at least to me. The only close to happy experience I have had coding with a small local model has been with Pi. Here is how I ran Pi and I was impressed how well it worked with a 9B model:

OLLAMA_CONTEXT_LENGTH=16384 ollama launch pi --model qwen3.5:9b

To get close to a happy experience with Claude Code or OpenCode with small local models I had to use 28B to 32B local models.

New comment by mark_l_watson in "GLM-5.1: Towards Long-Horizon Tasks"

mark_l_watson — Tue, 07 Apr 2026 20:19:04 +0000

I can’t wait to try it. I set up a new system this morning with OpenClaw and GLM-5, and I like GLM-5 as the backend for Claude Code. Excellent results.

New comment by mark_l_watson in "Show HN: Gemma Gem – AI model embedded in a browser – no API keys, no cloud"

mark_l_watson — Mon, 06 Apr 2026 13:05:44 +0000

I was thinking the same thing: better to run models using a local service not in the wen browser. I use Ollama and LM Studio, switching between which service I have running depending on what I am working on. It should be straight forward to convert this open source project to use a different back end.

That said this looks like a cool project. It is so valuable writing projects like this that use local models, both for tool building and self education. I am writing my own “Emacs native” agentic coding harness and I am learning a lot.

New comment by mark_l_watson in "Writing Lisp is AI resistant and I'm sad"

mark_l_watson — Sun, 05 Apr 2026 09:47:51 +0000

I am lazy: when an LLM messes up parenthesis when working with any Lisp language I just quickly fix the mismatch myself rather than try to fix the tooling.

New comment by mark_l_watson in "Writing Lisp is AI resistant and I'm sad"

mark_l_watson — Sun, 05 Apr 2026 09:44:43 +0000

I agree with you, but a Python REPL in Emacs (using the ancient Python Emacs support) is very nice: initially load code from a buffer, then just reload functions as you edit them. I find it to be a nice dev experience: quick and easy edit/run cycles.

New comment by mark_l_watson in "Writing Lisp is AI resistant and I'm sad"

mark_l_watson — Sun, 05 Apr 2026 09:40:05 +0000

Same experience. I like Haskell a lot but I am not great at Haskell programming. LLM based coding agents are useful for helping with runtime errors, library versions, etc. (and as other people here have said, for tedious stuff like cleaning up Emacs customizations, etc.)

New comment by mark_l_watson in "Writing Lisp is AI resistant and I'm sad"

mark_l_watson — Sun, 05 Apr 2026 09:29:05 +0000

Thanks for the Scheme setup examples. I have created very simple skills markdown files for Common Lisp and Hylang/hy (Clojure-like lisp on top of Python). I need to spend more effort on my skills files though.

New comment by mark_l_watson in "Writing Lisp is AI resistant and I'm sad"

mark_l_watson — Sun, 05 Apr 2026 09:23:42 +0000

Hey, thanks for mentioning Datalevin (https://github.com/datalevin/datalevin) - I hadn’t seen that before.

New comment by mark_l_watson in "Ruckus: Racket for iOS"

mark_l_watson — Sun, 05 Apr 2026 09:13:54 +0000

This looks good. I had recently removed all Apple dev tools from my Macs - decided I didn’t want to spend my time any longer supporting a platform that requires submitting personal use apps to the Apple Store just to make them persistent (not time out).

For Ruckus, I will reinstall Xcode, etc.

Other people have mentioned LispPad that is very good.

New comment by mark_l_watson in "Writing Lisp is AI resistant and I'm sad"

mark_l_watson — Sun, 05 Apr 2026 03:55:33 +0000

Interesting, and not quite my experience. While I do get better agentic coding results for Python projects, I also get good results working with Common Lisp projects. I do have a habit of opening an Emacs buffer and writing a huge prompt with documentation details, sometimes sample code in other languages or if I am hitting APIs I add a working CURL example. For Common Lisp my initial prompts are often huge, but I find thinking about a problem and prompt creation to be fun.

The article mentions a REPL skill. I don’t do that: letting model+tools run sbcl is sufficient.

New comment by mark_l_watson in "Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw"

mark_l_watson — Sat, 04 Apr 2026 16:25:48 +0000

Oh, https://opencode.ai/zen looks good. I like pay as you go plans since I usually don’t use many tokens compared to vibe coders.

I regret paying Google for a one year AI subscription last spring (although it was a deep discount over the regular $20/month cost) because it has kept me from experimenting with many venders (but it was a fantastic deal financially).

I just put a reminder on my calendar to try OpenCode zen when my subscription ends.

New comment by mark_l_watson in "Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw"

mark_l_watson — Sat, 04 Apr 2026 16:18:34 +0000

I am not the person you are responding to but I have tried both: using OpenRouter and also giving a Chinese company $5 on my credit card to buy tokens. If I know what model I want to experiment with, I much prefer to just pay $5 and have plenty of tokens to experiment. On a yearly basis, this is a very tiny expense for the benefits of getting plenty of tokens to experiment with.

New comment by mark_l_watson in "Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw"

mark_l_watson — Sat, 04 Apr 2026 16:05:55 +0000

I agree with you and the GP post, even though I am an LLM enthusiast.

My primary interest is using small edge models to perform specific engineering tasks. In this pursuit I do like to use gemini-cli or Antigravity with Claude a few times a week as coding assistants, but I am using relatively few tokens to do this.

I also waste a lot of time, but this is fun time: experimenting with open source coding agents with local models just to see what kinds of results I can get. This is mostly a waste of time, but I enjoy it.

My other favorite use pattern: once or twice a week I like to use the iOS Gemini app in voice mode, and once a month also use video input. I really like this, but it is not life changing.

Externalities matter: I never use frontier LLM-based AI without thinking of energy, data center, and environmental costs.

New comment by mark_l_watson in "Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw"

mark_l_watson — Sat, 04 Apr 2026 14:55:06 +0000

thanks! I never thought of using -p for using claude and gemini for one-shots and in shell scripts before. Nice.

New comment by mark_l_watson in "April 2026 TLDR Setup for Ollama and Gemma 4 26B on a Mac mini"

mark_l_watson — Fri, 03 Apr 2026 15:34:29 +0000

I agree with your criticism. I should have simply said that I had good results with gemma 4 tool use, and agentic coding with gemma 4 didn’t yet work well for me.

New comment by mark_l_watson in "April 2026 TLDR Setup for Ollama and Gemma 4 26B on a Mac mini"

mark_l_watson — Fri, 03 Apr 2026 15:21:54 +0000

I wasn’t very clear, sorry. By my ‘own research’ I meant spending 90 minutes experimenting with Gemma 4 models for tool use (good results!) and a half hour using with pi and OpenCode (I didn’t get good results, yet.)