back
user profile

mark_l_watson

21,400karma·8,624submissions·August 19, 2009
about
I am an author of 20 books and a practitioner specializing in artificial intelligence, deep learning, natural language processing, and the semantic web. I have 55 US patents. I code in Common Lisp, Clojure, Swift, Python, Haskell, Java, and Scheme. My web site is https://markwatson.com

My recent books can be read for free online on my web site or optionally you can pay for them at https://leanpub.com/u/markwatson

Twitter: mark_l_watson and Mastodon: @mark_watson@mastodon.social

recent activity (8,624 total)
comment
Hey, thanks for mentioning Datalevin ( https://github.com/datalevin/datalevin ) - I hadn’t seen that before.…
4mo ago·view thread
comment
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 App…
4mo ago·view thread
comment
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 E…
4mo ago·view thread
comment
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…
4mo ago·view thread
comment
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, …
4mo ago·view thread
comment
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 …
4mo ago·view thread
comment
thanks! I never thought of using -p for using claude and gemini for one-shots and in shell scripts before. Nice.
4mo ago·view thread
comment
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.
4mo ago·view thread
comment
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 goo…
4mo ago·view thread
comment
I spent two hours doing my own research before asking for Gemini’s analysis, which reinforced my own opinion that the gemini models historically have not been trained and target for agentic coding use…
4mo ago·view thread
comment
The article has a few good tips for using Ollama. Perhaps it should note that the Gemma 4 models are not really trained for strong performance with coding agents like OpenCode, Claude Code, pi, etc. T…
4mo ago·view thread
comment
For about two years I experimented with writing local apps using local LLMs, but I often had to blend in a commercial web search API to make my little experiments useful.
4mo ago·view thread
comment
I pay $13/month for Proton’s Lumo+ private chat LLM that contains an excellent built-in web search tool. I use it for everything non-technical, even just simple searching for local businesses, et…
4mo ago·view thread
comment
I have been using Apple’s built-in system LLM model for the last 7 or 8 months. I like the feature that if it needs to, it occasionally uses a more powerful secure private cloud model. I also write my…
4mo ago·view thread
comment
I love to see new Emacs Lisp projects, BUT: personally I prefer a simple ‘pure Emacs standard library’ experience as much as possible. I have been using Emacs over 40 years and this return to simplici…
4mo ago·view thread
comment
Looks good, but only Linux is supported. I like spinning up VPS’s and then discarding them when I am done. On macOS, something I haven/t tried yet but plan to: create a separate user account.
4mo ago·view thread
comment
Off topic but earlier today I asked Gemini to read this article and advise how to do the same things for OpenCode. I am fascinated with trying to get good performance from small local models.
4mo ago·view thread
comment
I think the value right now in LLM code assist tools is in small projects: small reusable libraries or proof of concept “I want this app even though almost no one else does” types of projects. For lib…
4mo ago·view thread
comment
I am biased: fully support the main ideas from Center Human Technology, books like Privacy is Power and Surveillance Capitalism, etc. This verdict is a good thing for society. I am not anti-big tech, …
4mo ago·view thread
comment
I was enthusiastic about early TensorFlow in Swift efforts, sorry when the effort ended. My interest then flowed into early Mojo development for a while. I wrote an eBook on Swift several ago but rare…
4mo ago·view thread
comment
I think this is a good learning project, based in a long perusal of the github repo. One suggestion: don’t call the CLI component of the project ‘claude’ - that seems like asking for legal takedown pr…
4mo ago·view thread
comment
Sometimes they do pay up. Google Gemini estimates that 25% of active daily YouTube users pay for ad free service. I know my wife and I do, and we watch a huge range of YouTube material more hours a mo…
4mo ago·view thread
comment
I also prefer seeing a corporation like Google do it for two reasons: generative content might feed their cash cow also known as “YouTube” and Google already has a good base for coding assistants. Goo…
4mo ago·view thread
comment
thank you!
4mo ago·view thread
comment
Good points. Perhaps there is a way to configure uv to only use a new version if it is 24 hours old?
4mo ago·view thread
comment
A question from a non-python-security-expert: is committing uv.lock files for specific versions, and only infrequently updating versions a reasonable practice?
4mo ago·view thread
comment
I agree! I used 'symbolic AI' for NLP starting in the early 1980s. Everything back then was so brittle, and very labor intensive.
4mo ago·view thread
comment
This looks so cool, just put it on top of my todo list. My Haskell skills are mediocre but I love the language. I get by with a subset of the language. Strong typing and data science seems like a good…
4mo ago·view thread
comment
I just spent an hour with Grafeo, trying to also get the associated library grafeo_langchain working with a local Ollama model. Mixed results. I really like the Python Kuzu graph database, still use i…
4mo ago·view thread
comment
Fairly much common sense advice, with some cultural taboos like resting chopsticks pointing to the right. I have always been a little embarrassed by my own use of chopsticks. When I was three or four …
4mo ago·view thread