mark_l_watson

OpenCode Go looked intriguing and I spent time reading their docs and pricing but didn’t purchase services. Do you think they are running it at a loss to get market share? (Probably not.) I have been happy buying tokens directly from DeepSeek (I am retired and everything I do is open source code and writing open content books (the manuscript files are available along with the source code) so I have no privacy issues). I also use FireWorks.ai to try different models. Both API services are excellent, but I may try OpenCode Go for a month or two to support the devs of OpenCode.

I want to say that I agree with you on the value of writing your own coding harness. I wrote something simple in Emacs Lisp and it makes me happy occasionally using it. I am trying to learn Rust and I am working on my own Rust core orchestration layer and I plan on both a Rust command line client and I already have a Python library wrapper for the Rust code that I have written so far. I write a lot of ‘little books’ and I am almost sure to write yet another one on my current hacking project.

Are my little hacks as effective as OpenCode or Claude Code? No way, but I am learning a lot and having fun.

I also use DeepSeek v4 flash and v4 pro, but I can’t settle between using Claude Code or OpenCode and it seems like I waste time switching back and forth (especially keeping my personal SKILLs files synced). On one hand, a ton of engineering work has gone into Claude Code, on the other hand all Chinese models I have tried with OpenCode seem well configured out of the box.

I was thrilled to have Gemini Ultra for a month and use as many Opus tokens with AntiGravity as I could use, but I am happier using less capable models like DeepSeek knowing that it is more fun to do more of the work myself, it is a smaller hit on the environment, and incredibly cheaper.

I spent a lot of time with RubyLLM a few months ago. Very nicely designed and implemented. I have my own LLM clients written in various Lisp languages and I thought about appropriating some of the design of RubyLLM. Imitation is flattery.

Thanks, interesting. Two years ago I wrote a text adventure game that used a LLM model. The system was very simple, but still was interesting. A friend of mine, Ben Goertzel, has been interesting in games/VR for a long while.

I wrote a book on the subject, but now really old material: AI Agents in Virtual Reality Worlds — J. Wiley, 1996

I had a Xerox 1108 Lisp Machine, ran InterLisp-D on it for about two years, then slowed it down by installing Common Lisp on it.

Wonderful for Larry et.,al. to keep it going as open source.

Out of principle. Also, I am an old man and retired - makes it easier to give up a little bit of productivity.

Yes, I do sound like a jerk. Difficult though to not worry about local bullshit a lot more than other country’s bullshit. While I care for every person on our planet, I spend more time thinking about the future of my children and grandchildren.

I live in the USA and I use a European LLM as a daily driver: Proton’s lumo+ that does a good job packaging a Mistral model for general chat, with good searchable chat history — all with adequate privacy guarantees. Well worth the money.

I purchase open model tokens for agent programming assistance, and I like lumo+ for everything else.

Another option is DuckDuckGo’s Duck.ai subscription, but I slightly prefer ProtonMail’s lumo+ packaging as a product.

The beauty of your approach: when people are not paying for an expensive subscription, they can decide to use models less and not feel like they are leaving money on the table.

But, it is not all about cost: models like DeepSeek v4 flash (I use the US company Fireworks.ai and also buy tokens directly from DeepSeek) is very fast, very low latency while working.

Would you want to use a text editor that updates the screen very slowly? Kind of the same thing for using agentic systems as coding assistants: don’t want a ‘sluggish’ experience.

Nice idea but expensive. It looks like they don’t add very low cost models like DeepSeek v4 flash into their mix.

After a few months of spending money on the best frontier models, now I am spending time using DeepSeek v4 flash as my workhorse, and flipping to more capable (but still very inexpensive) open models on an as-needed basis. We all make our own tool selection decisions, but for me, I feel happier and enjoy working more following the very fast response and ultra low cost path.

Potentially, the raising interest rates because investors don’t trust the long term stability of the UK economic system (more spending on pro-war activities, sluggish economic growth, and higher than expected government borrowing) will crash their financial system.

I hope I don’t sound too selfish but I am a USA citizen, and I would rather worry about my own country’s medium-term financial future.

Reading Rahul's post I got excited to build Emacs 31 from source, but reality occurred and I decided to wait for the release. I also like his articles on setting up Emacs.

I don't care what tools other developers use but in January I made my two dev Macs 'VSCode free' and use Emacs for everything. Feels better!

For decades I would spend tons of time experimenting with my Emacs setups but in the last few years I have been shifting to more out of the box experiences. I did write my own agentic coding platform in Emacs Lisp but I keep that separate from .emacs and .emacs.d

Why would my country blacklist DeepSeek? Perhaps crazy lunacy like: "Your product is too good and too inexpensive: consumers like US companies and individuals need to pay more for services."

Thanks, I put that on my Haskell note to try.

I am on a mobile device on vacation so all that I could do right now is read one of the notebooks.

Interesting idea but until I get my grubby little fingers in it, to try it - difficult to have an opinion.

I am hopefully expectant that we will see all sorts of optimizations in the next few years that will enable even more local model use and slash commercial API costs. I get excited by the results when I enjoy one or two short coding sessions a week with Claude Opus but it is even more exciting to get a major task done and see that I only used $0.05 for DeepSeek v4 Flash or perhaps $0.15 for DeepSeek v4 Pro. It was exciting in even a different way when I two shotted a complete TypeScript/Tauri app using gemma-12b-qat with little-coder on a cheap laptop a few days ago.

Sounds like a correct conclusion to me also. I am trying to transition to a layered system: local, then OpenCode with commercial vendor APIs for models like DeepSeek v4 flash, then DeepSeek v4 Pro.

With a layered approach we can slowly shift to running more locally and still get required work done. Really, my local setup is so much better than it was 2 months ago, and extremely better than 6 months ago - on the same hardware.

I would like to say I run 100% local, but I use Opus + Gemini Pro cumulatively for 3 or 4 hours a week. I also like to use DeepSeek v4 flash with OpenCode for small quick tasks.

I did just publish a free to read online book "The Rise of Local Coding Agents" [1] where I document my setup that I enjoy using. I use little-coder (built on pi) and have good results for small Python and TypeScript applications. I struggle getting good results with Common Lisp and Clojure.

For me, the problem with all local LLM-basic coding agents is slow runtime.

[1] https://leanpub.com/read/local-coding-agents

I have a question that perhaps you or someone else here has an answer for: I enjoy using Opus via Google Antigravity (usually agy) for perhaps 90 minutes a week. For Google’s subsidized $20/month plan they seem to give out a reasonably generous amount of Claude tokens. How does this compare with Anthropic’s $20/month plan using Claude Code?

BTW, I also use DeepSeek v4 Flash very frequently: fast and so cheap it is almost free.

I think Apple has a fairly good plan for supplying a common API and default on device models.

What confuses me about this article is: The code examples Python, Ruby, etc.) look to me like the original Anthropic APIs, not Apple’s abstraction. Did I miss something?

I am retired, so maybe I don’t get a say in this, but as a human who enjoys life in nature and hanging with family and friends, and also in periods of free time constantly exploring technology to understand the tools I use to the best of my abilities:

I find using minimal-capability local models or cheap commercial models like deepseek v4 flash to be the most satisfying because I am a major partner in solving problems or simply trying to better understand the world. I do like access to very strong models a few times a week.

A friend’s son and a young tech friend in town have very different views than I do because they are struggling in a tough job market and want a competitive advantage. I am grateful that I am not in that position.

This might be useful when ‘coding in chat mode’: I have a few scripts that I run in a project directory that takes a prompt from me, and creates a single long one-shot prompt that I can paste into a chat window and ask that any generating code is inside markdown code blocks for easier copy/pasting. Also, pardon the plug, but you can read my new tiny book free online that documents my experiences using agentic coding on my 16G Mac and my 32G Mac: https://leanpub.com/read/local-coding-agents

when I started using QAT recently, I stopped trying to improve my configuration after that. I will try tuning my local environment again in a few months, but with QAT things are good enough for now.

yes, whether for home experiments or at work, it is good practice (good hygiene) to be able to swap out both agentic harnesses and models. It is important to have a good strategy for exporting skills, etc.

Nice writeup, thanks.

I run something very similar except for directly using pi as the agentic harness I use little-coder that wraps pi with reasonable defaults for running local models. Even though my local setup is a bit slow, it is a thrill to do real work completely locally.

Thanks for your comment, I especially like “If you have software engineering skills and are not an accidental vibe-coder, honestly, try it out and stop burning money.”

I thought that using Opus with the Gemini Ultra subscription was in many ways awesome, but I simply feel happier using DeepSeek v4 flash with OpenCode (so fast!) of v4 pro when required.

I am on a wait list for the ‘better Siri model’ - what iOS and macOS betas just shipped with is awful. I do think the Apple Foundation Model built in to the system is better: I was using it from Python yesterday and it performs tool calling accurately and it is a very small model.

do you live in Phoenix?

I just asked Siri a few weather questions and named the city where I live, nailed it. My favorite digital device is my Apple Watch and if Siri improves over the next hear or two, that will be great for me.

Thanks apfel looks useful! I have been experimenting with Apple's foundation models for almost a year and they are useful for embedded applications. I have been taking a deeper dive into local agentic coding tools (starting with 'little-coder --model ollama/gemma4:12b-it-qat') and I put together a tiny free book with some setup advice that might save people a few minutes of setup time: https://leanpub.com/read/local-coding-agents

I have been fairly much pissed off at the "hype in hyperscaler" AI growth (data center environmental and other societal costs) and I support anything we can do to promote local and private AI.