Given how quickly things evolve, it’s easy to get lost in the numerous offerings and hard to get the best deal. So, what do you use? Both clients/harnesses and LLM providers or local setups would be interesting.
Personally, I’ve been using opencode with Github copilot for work. I’m currently looking for cost-effective provider for personal work. Maybe openrouter with one of the cheap models?
At work Cursor with Sonnet or Composer and very very few times Opus.
At home I can’t afford any of that so I use opencode and try to use super cheap models in openrouter and very few times to save money, I just delegate simple straightforward, tedious tasks to gemini flash or deepseek
Nothing. Fuck AI.
I use Zed with either Sonnet or Gemini. I do plan to swap to using Qwen locally since my hardware has no issues running it.
Nothing. I threw them all out. After is forgot how to write good code and how to design good software.
That his how cerebral atrophy must feel like.
If you forgot to write good code and good architecture, in a span of what, at most, a year, then you were never a good engineer to begin with.
I was worth every penny I earned 4 years ago. 1 year ago, I had to open documentation for C++ features I use for a decade. I could not remember how it works.
Your brain is a muscle, and sure, I had more time to teach, but I got worse at teaching because I got worse at doing
Not remembering specifics of a technology, and completely forgetting the base building blocks - the same blocks that you should be using for AI generated code too, BECAUSE YOU NEED TO FUCKING REVIEW IT - is not the same.
I’m an Android engineer by trade. I might not be able to give you the exact interface definition of a BroadcastReceiver, or explain in technical terms the core differences between a TextureView and a SurfaceView (that’s what the documentation is for!), but for sure as hell can tell you if your architecture is good or not, or if the quality of the code you wrote is shite.
I do not use AI to code; but I have been programming for two generations now.
I’ve taken a few breaks in that time, and switched technologies at least ten times also, and it’s very easy for me to forget a lot.
Programming is like any skill, it requires constant practice.
Am I a good programmer? Probably not that skilled, but I’ve written over a million lines of code and have run the gamut of architecture from: “Break this large file into 500 lines each, now we call that as a function” to “all numbers are object oriented” to “if it works great”
Claude cli almost exclusively. So far mostly opus, but I need to start using less expensive models more frequently.
I have Codex installed, but I mostly use it to interface with Obsidian, which is where I track all of my tasks and organization stuff. Unfortunately, codex doesn’t play cleanly with Claude, so it’s hard to use it for coding at all, but I do have it review documentation and identify gaps or discrepancies, because it’s far cheaper than having Claude do it.
I’ve tried lmstudio for local AI with some ~30b models. It works fairly well and fast, but only for tiny context sizes. One I pass a few thousand tokens the speed falls off pretty quickly.
In work we use cursor. I generally use their composer model. Before that it was vscode with claude.
Personally i have not done any personal dev work in a long time, its mainly server maintenance and i can do that myself. When i get the itch to do more dev stuff ill probably use vscode with copilot. My personal machine isnt great for local models.
I use opencode with locally-hosted llama.cpp - usually with qwen3.6-35b-a3b.
I tried opencode go for a couple month, and its definitely nice to have an lln runner with more gram and more GPUs, but I prefer to have all my stuff local whenever it’s possible. Also, I’d use up my token allotments fairly quickly on opencode go.
I also tried opentouter and it, too, was great - many more models. But I exhausted by credits even quicker than opencode go, and its also not local.
What hardware do you use? How fast is it?
AMD Ryzen 9 9950X CPU and AMD radeon pro w7900 (48GB vram). I get 55tps output pretty consistently, but ingesting context starts around 1500tps and if context size reaches, say, 50K, tps drops to around 200tps. I often have to wait a bit, but it’s a price I’m happy to pay for local-only AI
Thank you!
I’ve been using oh-my-pi agent harness with a mixture of Claude for planning and either Gemma4 or Qwen3.6 for execution.
How do you get your LLM credits? Or do you run Gemma and Qwen locally? With which hardware?
For Claude I have the lowest tier subscription through work. I also have openrouter to use occasionally when I need it. Gemma and Qwen I run locally on a strix halo framework desktop I bought just before ram prices went to the moon.
. Gemma and Qwen I run locally on a strix halo framework desktop
So, CPU only?
No, Strix halo is AMD’s integrated CPU GPU using unified ram. Its the non apple tax equivalent of the mac minis people have been using to run local models. On one hand its a bit slower as it has lower memory bandwidth and that’s the limiting factor, but on the other its less than half the price for more memory and runs linux rather than osx.
Excellent, thanks for the explanation!
I haven’t found anything that isn’t a shell backdoor that you let an llm run commands in, so strictly via chat interfaces.
I only use openwebui with an openai key that my employer pays for. No agentic stuff, haven’t found the need for that yet.
Good thinking to mention open-webui - I was only thinking agenetic coding, but I use open-webui for llm chatting. I think it’s fantastic.
I’m experimenting a lot with goose, recently return on by the AI arm is the Linux foundation. It’s not yet mature enough to recommend it as a daily driver for non fanatics though for agentic stuff.
Trying it as a daily driver by now :D
It’s less about the tool though in my opinion but about the process. If you want to be a programmer then you need something integrated into your dev environment in my opinion.
My focus is seeing how far I come with focussing in being a software architect who only has really weird junior devs who read a lot of books but lack any understanding.
Which is … quite close to real life ;)
I’m splitting by now my projects: agentic ones and “my” dev ones, treating trm differently helped me tremendously: different focus and I need a different skillset.
FYI, I think opencode go is kind of a subscription model, not a direct credits-to-tokens model. In terms of value it’s nowhere near as good as Claude’s subscriptions, but it seems way more valuable that paying for tokens directly. However they only offer a few models - decent ones, but not many and a little behind the times.
You can use opencode with a lot of different setups though, you don’t need to go for their subscription model.
Yes. You can use opencode, the agenetic coding tool, with just about any llm runner or model. But Opencode Go is their cloud-llm suscription plan, with limited/slightly-dated llm models.
I’ve just started playing around more seriously and I bounce between cursor and Claude code in CLI. I’ll check out how chat behaves and sometimes random tools like blackbox.
opencode with nanogpt (12$/month subscription or prepaid pay as you go) using GLM 5.1
let me know if you need a referral code for a 5% discount
You pay to write code?
https://github.com/cyberpapiii/chipotlai-max
sadly this doesn’t work right now
nanogpt
Do you know how nanogpt compares with openrouter? Why did you pick nanogpt?
I started using it for the web GUI, prepaid pay-per-usage model and as a more privacy focused alternative to chatGPT and such. Most months I was way under what I was paying to openAI (which ofc got all my data and knew what I was asking - creepy af).
Then I stayed for the API and started using the pro subscription.
