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. Google's gemini-cli and Antigravity for simple coding. Hermes Agent using GLM-5.1 on a dedicated VPS: all complex software design, deep research, large scale code refactoring, and updating book chapters with minor edits when I have modified software examples. ollama launch claude --model qwen3.6:35b-a3b-nvfp4: when I really want the joy of using a local model.

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, but it may still be of general interest: Apps vs. Web Browser On mobile devices (and my MacBook) I don’t like to install apps unless it is something like a Chess game app. Services like Email, Mastodon, Facebook, YouTube, and X all work fine in a web browser, even with the DuckDuckGo browser which is usually my default. Email I use my own custom domain on Apple iCloud email. Convenient enough. I use backup ProtonMail and Gmail accounts. I use the DuckDuckGo web browser, even on my iPhone, for these three services. AI vs. No AI Well, I have been a paid AI practitioner since 1982 b...

 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 thought reasoning if the model makes a quick guess at an answer, then that answer drives the remaining token generation process. Assigning a role to the AI assistant: for example "You are a historian who uses web search to verify your analysis of history and current events." Reverse prompting: explicitly tell the AI to ask you questions (important because modern system prompts often coach a model to not do this). One-shot or few-shot prompting As an example, you might want to process input text and save people's email addresses and names in some structured output forma...

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 to two million Chinese characters in a single prompt. Backed by major investors like Alibaba, Moonshot AI has quickly become one of China's most valuable AI unicorns and a key competitor in the global AI race. November 14, 2025 update: the code below is Python. I have more up to date Common Lisp examples using Kimi K2 here:  https://leanpub.com/lovinglisp/read#leanpub-auto-moonshots-kimi-k2-model The release of Kimi 2 last week has been referred to as "another DeepSeek moment." You need a Moonshot API access key from  https://platform.moonshot.ai/console/account The direct AP...

 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 from LLM use and it seems like Google is striking a good middle ground in cost and environmental impact. Automating NLP and other workflows seems fairly simple: automate writing pipeline requests to a JSONL file, automate sending requests, periodically polling for the results being complete, auto-download and use results in your workflows.

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 location to another. Yesterday I was really in the mood to do something fun. We didn’t have anything going on for Fourth of July celebrations until an outdoor symphony in the early afternoon, so I sat down in the morning with Google‘s excellent Gemini CLI coding agent and I described what I wanted, which was to be able to input a story context as a text input file and then use an LLM in a conversation loop and continuously provide you with the text based adventure program experience. I was really surprised how well it turned out. Fun! The generated adventure game code uses a local model running ...

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 hardware-software co-design with standardized protocols for interoperability enables US institutions to maintain a competitive edge. Simultaneously, promoting collaborative frameworks for data sharing, federated learning, and algorithmic auditing mitigates risks of siloed innovation, ensuring that breakthroughs in efficiency, low-latency inference, and energy-optimized training regimes benefit a global network of research and industry stakeholders. In the USA I would like to see major resources dedicated to both open models such as the ones from Meta, as well as the use of French Mistral open mo...

 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 going back to using OpenAI O1 and Claude Sonnet, but after my preliminary tests with Deepseek-R1, I feel like I can do most everything now on my personal computer. I am using:  ollama run deepseek-r1:32b I recently published my new book “ Ollama in Action: Building Safe, Private AI with LLMs, Function Calling and Agents ” that can be read free online at  https://leanpub.com/ollama/read

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 hardware since I don’t want to take the time to move my data and general workflow to a Pixel phone. The iPhone is the strongest lock-in that Apple has on me because of the time investment to change. The main reason I am feeling less interested in the Apple ecosystem and platform is that I believe that our present day work flows are intimately wrapped up with the effective use of LLMs, and it is crazy to limit oneself to just one or two vendors. I rely on running local models on Ollama, super fast APIs from Groq (I love Groq for running most of the better open weight models), and other APIs from Mist...

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 the PDF for my book "Practical Artificial Intelligence Programming With Clojure ( you can read it free online here ) and used it to create a notebook in Google's  NotebookLM  and asked for a generated 8 minute podcast. This experimental app created a podcast with two people discussing my book accurately and showing wonderful knowledge of technology. If you want to listen to the audio track that Google's NotebookLM created,  here is a link to the WAV audio file Last week I signed up for a one year plan on  Replit.com  after trying the web based IDE for Haskell and Python...

 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 year subscription. I quickly rewrote a complex Clojure web app I wrote 12 years ago in JavaScript making it much less expensive to host  CookingSpace.com  (new JavaScript version) I gave a live demo of Replit AI in my weekly AI demo and group chat. Please join:  Mark Watson's informal AI presentations and group chats