Previously, both tools and providers:
- Continue.dev (kind of broken regardless of models)
- Aider (unpleasant for me to use, too much busywork)
- GitHub Copilot (tbh nice plugins and generous quotas + the only working autocomplete that's actually good I've tried)
- JetBrains AI and Junie (since I already pay for their IDEs, that came bundled), also nice but quotas are quite limiting
- local models with Ollama or llama.cpp - cool conceptually but always really limited
- OpenRouter for cloud models - ended up being kind of expensive and I didn't need those various models that much in the end
- Cerebras Code - really generous token limits and amazing speed, but recently more downtime and not as stable, and I realized I need SOTA models
- OpenCode - honestly pretty good
- Codex - also pretty good
Right now:
- Anthropic Max (100 USD a month) subscription has pretty much replaced everything else
- Claude Code, both the CLI and GUI version has replaced everything else, good enough, also doesn't have *as many* file path issues as OpenCode (e.g. on Windows)
- still using Docker containers for builds, but also running it directly on my system because I'm lazy and stupid, no claws of any sort though
Overall thoughts on development:
- even the good models will create untold amounts of slop, unless controlled
- that's why I'm creating a tool called ProjectLint for my own needs, where you can write rules in ECMAScript (Go + goja) for what a project needs - stack agnostic rules in regards to the code structure, architecture, utilities that must or must not be used, file lengths and where to put them, which tbh in practice ends up being a shitload of regexes instead of ASTs, but at the same time that's good enough - there's consistent output with suggestions of what to do for each error; LLMs love that shit
- other than that, Opus 4.6 for everything currently, really nice tool use, good web search for referencing stuff (no documentation MCPs yet to keep it light), digging into node_modules or other source code to realize what's up, often MULTIPLE parallel code review agents, since just one often isn't enough
- also you really, really need code tests and the ability to stand up a local environment - I used to hate projects before that don't have these, now I just hate them with an even more of a burning passion
- I've done in a few weeks than people do in a month, not 10x but definitely an improvement with any work that has friction in it (I probably have unmedicated ADHD tbh), though the context switching will absolutely burn people out and having the ability to write code will athropy when you're just having more work thrown at you and outsource more and more of the development to these tools, plus if they hike the platform prices that's gonna be painful too
- In plain words, for a while it's gonna be great but long term we're cooked, also interesting to see that if you try to use these tools without a modicum of actual engineering in regards to how to approach these, you will often still get shit results long term, even with good models