I started with ChatGPT, then moved on to Claude, and then discovered Grok. But now I've stopped paying for any of them. Claude edged out ChatGPT in quality, while Grok stood out with its generous usage limits. That all changed, though, once they rolled out the agent system and RLHF. Suddenly, the model slowed to a crawl, veering off on wrong paths and getting lost in its own reasoning. Those endless, super-annoying RLHF popups didn't help either.
My theory? They were scrambling for a competitive edge and were willing to swallow some short-term pain. Plus, it feels like they shifted focus away from keeping coders deeply in the loop.
In the end, we vote with our wallets—if it doesn't click, just walk away. I still dip into Grok, but only the free tier: Grok 4's fast mode for tackling planning and first generation, and then Qwen Coder for the code editing and clerical tasks. The latest version of grok hold up about as well as the old Grok 3, just with way more steps...
I guess I joined Claude late, but its been working pretty decent for me. I've been using Claude Code with Zed now that it's a native feature. Honestly, if you're building coding APIs for your LLM and you aren't working with the Zed folks to get your model natively in that editor, you're messing up big in my eyes, its just done so well.
My biggest gripe with Grok is they're not really integrated in all the great tooling I use. I know I can use an API key with Zed, but come on, you want to compete with something like Claude Code? You need to integrate with the tools devs actually use. If they want to rush on anything, get it on more tools.
I complained to them about the missing CLI. That was probably the last straw that made me decide to stop paying for it. They could deliver a CLI with calls included in SuperGrok, and a lot of people would stop using Gemini CLI and Qwen Code.
My theory? They were scrambling for a competitive edge and were willing to swallow some short-term pain. Plus, it feels like they shifted focus away from keeping coders deeply in the loop.
In the end, we vote with our wallets—if it doesn't click, just walk away. I still dip into Grok, but only the free tier: Grok 4's fast mode for tackling planning and first generation, and then Qwen Coder for the code editing and clerical tasks. The latest version of grok hold up about as well as the old Grok 3, just with way more steps...