mark_l_watson

Using Zed with ssh is an interesting idea. I spend a lot of time mosh/ssh to VPSs, then running 'emacs -nw' locally on the server. This is a great setup since I love Emacs, but I will give Zed/ssh a try. Thanks.

I experiment a lot with local models, great results for engineering tasks, less so for coding agents.

I have used the following on a 32G MacMini to help write useful code:

ollama launch claude --model qwen3.6:27b-coding-nvfp4

The problem is that running local models (except for engineering tasks like data munging) is slow. With the above setup I set up a task (asking for no user verification) and go for a walk to wait for results that my Gemini Ultra plan would produce in 10 seconds.

I love LLM tech and want to see it support viable long term businesses that don't rely on losing money providing subsidized subscriptions that lose money. I ranted about this on X yesterday, primarily about a legal framework to prevent LLM dumping: https://x.com/mark_l_watson/status/2049221176657129794

Same for me!

My .emacs config has improved and I wrote my own Emacs based coding agent https://github.com/mark-watson/coding-agent

Indirectly I use Mistral daily: I like Proton’s Lumo private chat and that runs on Mistral technology. Something like Lumo is very much good enough to replace search and general information browsing and for me is very practical.

What is not so practical is my paying for Gemini Ultra, which has some practicality but is something I pay for because it is fun using strong AIs like Claude and Gemini Pro in AntiGravity. It feels funny to admit paying a lot of money just to have fun with something.

I wish Mistral good luck, and I like their deployed forward engineers approach to business. Seems practical.

A friend taught me and a few other friends how to play Mahjong early this year. Great game! You do need a skilled instructor and four people to play. This article is good, I wish that I had it five months ago.

So much of the public hates AI, at least the non-tech people I talk with. Good to see so much common sense among the general public.

While I find a Gemini Ultra subscription worthwhile for myself, most of the value is in the fun and entertainment of interacting with a strong API in AntiGravity (usually use Claude models), Gemini App, NotebookLM, etc. It is intellectually interesting and fun.

Can I justify the cost to society for data centers, possibility of US government bailing out the AI tech giants, etc.?

No I can't. I think the Chinese are skunking us. Building cheaper AI is the winning strategy. GLM-5.1 and Deepseek v4 are amazingly effective for much lower inference costs.

I live in Emacs, but I will give Mine a try when get a free hour. I read about Coalton in X and follow the author but I haven't invested time yet to try out.

This is an interesting conversation: some of you correctly pointing out that so much AI driven development is not having a positive effect on business profitability, and others correctly pointing out positive results that give evidence for great future progress.

I have an unusual set of metrics for evaluating AI. I am old and comfortably retired but I still like to experiment with AI tools for updating many of my old (or ancient) open source projects and creating new projects. I am blown away by how good my dedicated Hermes Agent setup on a VPS and also running Google AntiGravity with Claude and Gemini are. Both systems are unbelievably good.

I can only imagine how effective companies with a solid engineering process will be as appropriate roles for human and AI developers solidify. I can also imagine companies with a poor process and poor engineering taste will waste a lot of money.

The flash version is smaller, I think around 200B parameters and is cheap to run.

I used the flash version on a tricky Common Lisp coding problem this morning. The first cut of the new library had a runtime error. I was running in a simple REPL using:

ollama run deepseek-v4-flash:cloud

so I had to feed the generated code and the error back into the REPL manually, but it nailed it the second time, and the Common Lisp code was very good.

I have been running the slightly larger 31B model for local coding:

ollama launch claude --model qwen3.6:35b-a3b-nvfp4

This has been optimized for Apple Silicon and runs well on a 32G ram system. Local models are getting better!

I have an old Mac Mini with 32G of integrated RAM, and the following works for me for small local code changes:

ollama launch claude --model qwen3.6:35b-a3b-nvfp4

In addition to not having an integrated web search tool, one drawback is that it runs more slowly than using cloud servers. I find myself asking for a code or documentation change, and then spending two minutes on my deck getting fresh air waiting for a slower response. When using a fast cloud service I can be a coding slave, glued to my computer. Still, I like running local when I can!

I am on Google's $20/month plan, and I usually get about three half-hour coding sessions a week with AntiGravity using the Claude models. The limit using Gemini Pro models is much higher. I am retired so Google's $20 plan is sufficient for me, but I understand that people who are still working would need higher limits.

I am also on a $10/month plan with Nous Research for supplying open models for their open source Hermes Agent. I run Hermes inside a container, on a dedicated VPS as a coding agent for complex tasks and so far I find the $10/month plan is enough for about five to ten major tasks a month. I think it is also a good deal.

I hope this is not off topic, too much: with the current geopolitical situation I expect reduced capacity to manufacture both memory chips and all types of CPUs/GPUs. I base this on news I read from: Japan, South Korea, and Singapore.

If I am correct (and I hope that I am wrong!) this will drastically increase the cost of building these new data centers.

I ran OpenClaw in a container, on a VPS without connection to messaging systems, so perhaps that is why I didn't get value.

Similarly, I have been using Hermes Agent also inside a container, and on a VPS with only access to a local directory in the VPS with a dozen active projects on GitHub. I don't give it access to my GitHub credentials, but allow it to work in whatever branch is checked out.

This setup is fabulously productive. I use it about every other day to perform some meaningful task for me. It is inexpensive also. A task might take 20 minutes and cost $0.25 in GLP-5.1 API costs.

So TLDR: out of the box, I use Hermes at least one hour a week and find it to be a wonderful tool.

The new movie Mercy is a good take in this, as fiction.

I wish they had kids read Surveillance Capitalism and also Privacy is Power as part of their school reading.

Well, I started a long time ago: I had written several books and readers occasionally contacted me for doing gig work.

I enjoyed both of your long comments, thanks!

I would add one thing to the programming languages conversation: which languages make developers happy to use them? Personally, I have no emotional involvement with Python (sometimes the practical choice, but no excitement). I love using Lisp languages, and enjoy Haskell even though I am not a particularly good Haskell programmer.

I used tools that I was paid to use. After being deep in neural networks in the 1980s, ten years ago I dropped back into deep learning, thus mostly used Python.

I agree and I am amazed at how much money some individuals and also a friend's company burn on token costs. I get huge benefits from this tech just using gemini-cli and Antigravity a few times a week, briefly. I also currently invest about $15/month in GLM-5.1 running Hermes Agent on a small dedicated VPS - fantastically good value for getting stuff done and this requires little of my time besides planning what I need done.

I think the token burners are doing it wrong. I think that long term it is better to move a little slower, do most analysis and thinking myself, and just use AI when the benefits are large while taking little of my time and money to use the tools.

Clojure is a great language and ecosystem. I donated a little money to Rich's efforts in the early days (I loved his older Common Lisp - Java bridge so his Clojure project was immediately interesting) and I have been paid for a few years of Clojure development.

I like maintaining the history in one place, nicely done.

I don't use Clojure much anymore, but two hours ago I updated two chapters in my old Clojure book because the examples had 'gone stale' and that was fun.

While I liked to see a native (written in Swift?) app, the web interface for Gemini is very usable.

I find OpenClaw and (more so) Hermes Agent useful for software development, research, and writing - but I refuse to run them anywhere that is not deeply-sandboxed and has no access to most of my digital life data.

OK, everyone makes their own decisions re: privacy and security. Personally, I am comfortable running OpenClaw and Hermes Agent on a rented VPS (preferably in a docker container on a VPS) and allow limited access to (some of) my GitHub repos. Both tools are useful, even in such a limited mode of operation. I just don't see value vs. risk allowing access to email, messaging apps, access to my personal computer, etc.

It is close to zero overhead to SSH/Mosh to a VPS, get inside a container to work. Why risk infecting your personal or corporate computer?

At the time his friends and family in interviews talked about how happy he was: after whistle blowing and leaving to start his own company. The scary thing is that there were so many huge investors who might have had him killed. People are weird when there is a lot of money involved.

I agree. At first I was really turned off by the Gemma 4 line of models because they didn’t function with coding agents as well as the qwen3.5 line of models. However, I found that for other use cases Gemma 4 was very good.

EDIT: I just saw this: “”Ollama 0.20.6 is here with improved Gemma 4 tool calling!”” I will rerun my tests after breakfast.

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

looks nice!

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.

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