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?
A mix of gpt-5.5 and claude opus 4.7, wrapped in my own mobile web UI that doubles as planning software and document editor.
The reason for the mobile focus is I’ve been trying to detach from my home office as much as possible, meaning I do a lot of up-front planning via ADRs and task/story writing, then I spawn agents to actually work on coding tasks. The only part that really requires sitting at a desk is code review, manual testing, and deeper human-in-the-loop coding or debugging sessions.
If you are able to max out the $100/mo plans from either OpenAI or Anthropic, then that is already a very cost-effective option.
I don’t like the term “AI coding”, but recently I have been playing with opencode with it’s hosted models and ollama for light local models. It’s good as a rubber ducky, an assistant, or co-programmer.
At work claude code, at home zed+deepseek. I loaded up a few dollars in deepseek’s API and they are lasting a long long time (many months). I also tried qwen locally but it’s too slow for me (it runs on the CPU…). I use AI though only for repetitive and boring implementation tasks, or throwaway one-time scripts that I don’t feel like coding by hand. The point of coding at home for me is to have fun, and having the AI solve all interesting problems for me defeats entirely the purpose of why I’m coding. At work we are unfortunately being pushed to use AI a lot more, and the amount of slop code is increasing :(
Claude Code, mostly, but I’m with Scipitie that the tool matters less than the process around it. What’s helped most is writing the project’s rules and conventions into files the agent reads each session, then putting the non-negotiable ones behind a linter or a test so it can’t quietly skip them. Treated that way it behaves a lot like the junior who’s read all the books and understood half of them. Left to its own judgement it drifts, which is the part the guardrails are there to catch.
OpenCode Go/Zen have deepseek models that have the best cost-benefit out there. Then OpenRouter with selected providers if I want to try something else.
I don’t spend more than $20/month on personal projects and still manage to have a lot more functionality than I could have without 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.
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
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’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.
Nothing. Fuck AI.
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.
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’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.
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.
That’s not how a brain works.
People forget the language they grew up reading/writing/speaking simply because they stopped using it.
That’s… precisely how the brain works.
We’re not talking language specifics here. We’re talking about core principles of software engineering - principles that can be applied easily to other aspects of life. We’re talking about patterns, concepts, best practices.
Things that one needs to utilise daily even with AI generated code - that is, unless you’re checking in whatever the AI writes with zero review.
They actually do, and unless you talk in code this is more akin to a second or third language, not the one you grew up with. I have personally noticed how after a year or so of using the rng machine I simply could not code without AI, and am now lucky to be rehabilitating myself. There are already serious studies about the deskilling effect, this IS how it works. “AI” (meaning the LLMs now thrown at every thinking problem) is a lazy enshittifying tool.
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”
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.
If I can’t remember a specific interface I can not judge if would be the right tool for the given job. Using suboptimal tools is bad architecture for me.
That’s just a simple example.
It took me about 8 weeks to get back up to my old productivity, and suddenly code that looked perfectly fine from agent backed project’s give me nightmares.
Not remembering an interface is easily alleviated.
Forgetting core architectural principles - which are the cornerstone of good architecture - cannot be fixed that easily.
Micro details, specifics, are what the docs are for. You don’t need to remember the specifics as long as you have the understanding of what the thing does.
Macro details - appropriate information and event pipelines, SOLID, KISS, etc., are what architecture is about. You can write the best micro-scope code if the end result on a macro level is spaghetti that would feed Rome for a year.
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.
