I am a consultant and the author of 20+ books on artificial intelligence, machine learning, and the semantic web. 55 US patents. My favorite languages are Common Lisp, Haskell, Clojure, and Python. I live in Flagstaff Arizona. My personal web site: hire me for part time work! Privacy Policy: My blog is hosted on Google's Blogger service.
These are my notes: Setup # Install Docker and the Colima container runtime brew install docker colima # Start the runtime colima start (Note, I had to run: colima stop -f ; colima delete — then run Colima start again) # create docker image: docker run -d \\n -v "$(pwd):/workspace" \\n -v ollama_data:/root/.ollama \\n -p 11434:11434 \\n --name ollama-dev \\n ollama/ollama:0.21.0\n docker exec -it…
I try to only change my default tool stack slowly. Stability saves time at the cost of missing out on the fun of continually trying new things. To get stuff done, and since I am retired this is mostly writing, creating new example programs for my books, and updating older books, I rely on: Proton's Lumo private AI Chat: almost all web searching and casual AI Chat. Google's Gemini: research.…
I just rejoined the FSF ( https://www.fsf.org/ ) recently after almost ten years of not being a member. For decades I relied on Linux for work and writing and being a member of the FSF made sense. However when I decided to simplify my life and use a MacBook, an iPhone, and an iPad I let my FSF membership drop. I am enjoying being a member again. I am not recommending that anyone adopt my setup,…
I cover the use of LLMs in several of the books I have written . This blog post is meant to be common general purpose advice for effectively using AI using four techniques: Use one-shot or few-shot prompting: show the AI what you want with examples. Chain of thought reasoning: LLMs are auto-regressive models so the tokens generated "become part of the prompt," that is, without asking for chain of…
Moonshot's new Kimi 2 model is extremely inexpensive to use. Moonshot AI (月之暗面) is a prominent Chinese artificial intelligence startup focused on developing large language models with the long-term goal of achieving Artificial General Intelligence (AGI). The company gained significant recognition for its Kimi chatbot, which pioneered an exceptionally large context window capable of processing up…
I noticed on X this morning that Google dropped a new batch API with a 50% price cut. I use gemini-2.5-flash for speed and low cost and being able to batch large numbers of requests in a JSONL file (JSON where each line is a single legal JSON expression) seems like a big deal to me. Gemini Batch API Docs I have been a little negative on Hacker News and X recently about the energy costs vs. value…
In the late 1970s, I worked long hours on a text based adventure game called land of the dwarf for the Apple II computer. My game was written in Apple Basic and I gave it away for free. I wrote it using a huge sheet of paper, drawing a transition network diagram with bubbles, locations and action codes for things that could be done and arcs between the bubbles being the ability to move from one…
I would like the USA to not lose the ‘AI race’ but I don’t want other countries to lose either. Ensuring continued US leadership in AI without constraining global progress necessitates a dual-pronged strategy that couples strategic national R&D investments with adherence to open international standards. On the technical front, integrating edge computing, specialized AI silicon, and advanced…
I spent a few days experimenting with Cursor last week. Bytedance's Trae IDE is very similar and is currently free to use with Claude Sonnet 3.5 and GPT-4o: https://www.trae.ai/home I would like to use Trae with my own API accounts but currently Bytedance is paying for LLM costs. I have been experimenting with the qwen2.5 and qwen2.5-coder models that easily run on my M2Pro 32G Mac. For reasoning…
I have been been playing with the Apple Intelligence beta’s in iPadOS and macOS and while I like the direction Apple is heading I am getting more use from Google’s Gemini, both for general analysis of very large input contexts, as well as effective integration my content in Gmail, Google Calendar, and Google Docs. While I find the latest Pixel phone to be compelling, I will stick with Apple…
Putting "closer to AGI?" in a blog title might border on being clickbait, but I will argue that it is not! I have mostly earned my living in the field of AI since 1982 and I argue that the existence of better AI driven products and the accelerating rate of progress in research, that we are raising the bar on what we consider AGI to be. I have had my mind blown twice in the last week: Today I took…
I have only spent a short while experimenting with the ne gtp-o1 models: so far very impressive for science, math, and instruction following. You need a ChatGPT Plus account to try it, or you can perform rate limited queries for half the monthly cost using Abacus AI The thing I am most impressed with (this week!) is the Replit.co AI coding agent that after briefly trying it I pre-paid for a one…
I wanted to convert my server side web site CookingSpace.com to mostly client side JavaScript. I used the Replit.com AI coding agent to do this, and while this is a subject for another blog article, I showed the Replit coding AI a snippet of my JSON recipes and nutrients file, and described in a few paragraphs the functionality of the new web site. I want to share a recipe that I created: Mark’s…
Topics: Large context prompts with LLMs vs. RAGs using embeddings vector stores. How to avoid LLM hallucination. 3 code demos. started an informal code demo and group conversation Meetup group (link) and today I gave a fifteen minute code demo followed by a conversation with the attendees. Here is a GitHub repo with the code examples: https://github.com/mark-watson/talk2_LLM_Python_intro Here are…
Robert Oppenheimer and Edward Teller facilitated my Dad getting a professorship at UC Berkeley when I was 3 years old. Oppenheimer left Berkeley but Teller was a good friend of my father and I remember him being in our home. Three weeks ago, my wife and I were just leaving to see the new Oppenheimer movie when my Dad called. He mentioned that when I was in grade school he was invited to give a…
As humans we have evolved over a few million years to be both attentive and reactive to danger, live in social communities, and spend much of our time being in the present moment gathering and eating food and socializing. The behavior of rapidly changing short attention to content on social media, too many good short form things to watch on streaming video entertainment platforms, are all rewiring…
In the 1940s von Neumann and his colleagues created conceptual models for computer architectures that were oriented toward the engineering problems of building computing devices, and not for making it easier for humans to write programs. The Lambda Calculus and also the design of the Prolog programming language are the first real efforts that I am aware of to place emphasis on how we humans think…
I find it sad that Musk's purchase of Twitter is turning out so badly. I read that advertisement pre-sales for next year are very low, thus the urgent need to cut expenses. I don't dissagree with Elon Musk's original idea of having an uncensored platform, but the execution is not good. My best wishes to everyone at Twitter (and other tech companies) who have lost their jobs recently. The job…
I read with some humor my last blog post from 6 months ago, saying that I was retired. Ha! As I mentioned 6 months ago, my wife has chronic health problems but those have stabalized, and life is now fairly good. I did start a very much part time (15 hours/week) advisory gig with Mind AI about 4 months ago. Enjoyable work on an interesting product. I am not performing any substantial development…
What does an intelligent person do in retirement? That is a question of individual tastes but I will share my list of 20 things. Yesterday was my last day working on a recommendation model at Babylist. Babylist is a great company to work for but I decided to retire in order to spend more time helping my wife who now has chronic health problems. When I write books, my wife enjoys editing my work so…
Like most people, there are many more things that I would like to do than I have time to do. I believe that learning to identify action items that simply should not be done is valuable, but not easy to do. I am mildly attention deficit in the sense that I can only think about or attend to one thing at a time. For a computer scientist, this has been a super power, but is personally inconvenient. I…
I prototyped a simple natural language question answering demo in about 90 minutes. I accept a query like “where does Bill Gates work?”, find the likely URI for Bill Gates, collect some comment text for this DBPedia entity, and then pass the original query to the transformer model with the “context” being the comment text collected via a SPARQL query. I run this on Google Colab. Note that I saved…
I retired (my last job was Master Software Engineer and the manager of a deep learning team at Capital One) a year ago April and was enjoying time with friends and family, doing personal research in hybrid AI, lots of writing, and volunteering at our local food bank. I stopped my volunteer work with COVID-19 and welcomed the opportunity last month to start work at Olive AI working on a very strong…
My wife Carol and I have been practicing social distancing and wearing masks for shopping for over 5 months now. Welcome to the new normal and a crazy world in which entertaining and seeing friends is done by meeting in people's yards and everyone bringing their own "meal in a bag." I enjoy writing so I have been updating my recent books, starting with Loving Common Lisp, or the Savvy Programmer's…
Here are some of my of my recent notes that might save you some time, or teach you a new trick. I have had good results using the py4cl library if I wrap API calls to TensorFlow or spaCy in a short Python library that calls Python libraries and returns results in simple types like strings and dictionaries. I just committed a complete example (Python library and Common Lisp client code) to the…