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
I use LLM_based coding agents frequently with Lisp languages and my way of working is different with Lisp languages: 1) if generated code ever has a syntax error, I like to quickly fix the syntax error myself. 2) for some reason I usually prefer to run tests myself in another terminal (with Python, Typescript, etc. I let the coding harness run tests).
I haven’t let coding harnesses run REPLs. When I do let a coding harness run tests I specify in, for examp,e, my Common Lisp skills file to run ‘sbcl -load …” so bash test commands are one liners.
It would be interesting to work on skills and a harness to use REPLs - nothing bad about that idea, I just haven’t tried it.
Nice, I like the functionality and that it is a tiny native SwiftUI app. I recently wrote a blog [1] on using Apple containers for agentic coding; I just updated it to mention Davit. I so much prefer using Apple containers to using Docker on my two home Macs for personal projects.
re: "So, first, by no measure is GLM5.2 as good as Opus."
I accept that for you and your work this is true.
I have a different experience: for a month I paid big money for Opus and got a lot done. Now I am gorging on GLM 5.2 running on Fireworks.ai and I am also getting a lot done for about 15% of the money.
Everyone should do their own evals on their own work.
Good point, I also like to do the work myself, with an assistant under my control. I am usually really happy with DeepSeek v4 Flash that I feel just mostly does what I tell it to do, but I do switch to Pro for harder tasks.
There are so many models, and I personally ignore benchmarks so it takes some time to try different models on my use cases. Fortunately, it is ‘good enough’ to do the work to find a few models that work for me, and just use them for a month or two before re-investing time for my own evals to possibly change models.
People should evaluate what works for them and ignore other people and benchmarks. (Apologies if that sounds snarky.)
There are several general types of tasks that a Gemma 4 12B class model works for me, including: 1) design a large project composed of small libraries that can be coded and tested in isolation. 2) clean up old coding projects: add README files, comment code, show an example of using a new API and have it update API use, etc.
All small-scale stuff. For large integrated projects I am finding DeepSeek v4 Pro commercial API to be very inexpensive and helps me produce good results.
I can come close to agreeing because queen-3.6-27b is my second favorite for local coding. I am using gemma4:26b-a4b-it-qat-48k (the "-48k" is from my modifying a model run with Ollama to always use a 48K context size). On a 32G Mac I use gemma4:26b-a4b-it-qat-48k and OpenCode and on my 16G MacBook Air I use gemma4:12b-it-qat-16k ("-16k" is my resizing context size) and little-coder. I break up projects into small libraries because local coding works better for me using small code bases.
I find that for local coding, I need to spend a lot of time building concise SKILLs for specific things I work on and try to only enable one or two skills per coding session.
To the author of the linked article nice job, and if you feel like adding to it, please add details on your setup.
Misleading title on HN but an interesting article, a reminder of why the hyper scalers are investing heavily in infrastructure.
That said, I expect much of the AI bubble to pop. Google Gemini with Antigravity is a good product, as is a Claude Code subscription but I have switched to using DeepSeek v4 Pro with the Claude Code harness and DeepSeek v4 Flash with the OpenCode harness (when I am not using local models with little-coder/pi) and at least for the foreseeable future I don’t think I am going back. Fast APIs at low cost trumps having to spend a little more time to get the same quality of results.
Your experience with DeepSeek v4 Flash differs from mine: while I usually use DeepSeek v4 Pro (that is also inexpensive), I find using DeepSeek v4 Flash with the Fireworks.ai API and properly configured OpenCode to be very good for routine work, and it is pleasantly very fast. Admittedly I use DeepSeek v4 Pro for difficult problems.
I encourage people to at least once a month to do a quick evaluation with their own problems and workflows. Estimate cost as both what inference tokens cost for a task and also how much human effort it takes to get required results.
I was expecting this. Glad I just upgraded my wife and myself in December.
One fix for this problem: Allow US companies to buy memory chips from China. I saw an article about a month ago, that if my memory is correct in this, said that China is ramping up high-end memory manufacturing.
Fix number two: my country (USA) should cease and desist with the craziness that is data center buildouts for AI.
Clearly ‘BIG MONEY’ always needs a new thing (cloud -> crypto -> AI) and the powerful get what they want.
If the US Congress acted to benefit regular people rather than special interests (both party's are corrupt, disbelieve that if you want to live in a fantasy land) then anti-dumping laws would be passed.
If all companies and individuals paid the real price for tokens, then we collectively would work more efficiently. As is, the filthy rich get even filthier, and regular people will get screwed.
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
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: @[email protected]