Ask HN: What do you currently use for AI coding (personal or professional)?
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? Opencode can be connected to Qwen for coding grunt work. It's pretty decent, but I prefer to use Claude. Less mistakes, better for reasoning architectural decisions with the agent checking against the existing codebase and documentation. I also keep things sandboxed in yoloAI for peace of mind and to eliminate permission fatigue. Do you pay for the model? Or run it locally? If so, which hardware do you use? Is it fast? I use an RTX 3090 with 24gb on it, which can comfortably fit https://huggingface.co/Qwen/Qwen3.6-27B. It's freely downloadable, so you only pay for the gfx card and the electricity. There are also plenty of models out there that work well on Apple unified memory. But mostly I just use Claude now since I already have a max subscription. I've done hybrid setups in the past where I had Claude do the hard stuff and a local LLM do the code monkey stuff, but with the right optimizations I'm no longer hitting the Claude token ceiling. Thank you ! Cool to see more people building phone-first agent control. I've been working on the permission layer side of this same problem. One thing I learned: session management and permission approval have very different latency requirements. Sessions you check every few minutes. Permission requests need sub-second response or your agent sits idle burning tokens. Push notifications > browser polling for that reason.