quanwinn

Love this! Was the UI done with Claude or some LLM? Not a critique, just curious because the designs give off that vibe to me.

Using AI to code doesn't automatically mean bad code. Although I suspect the majority of AI code will be subpar.

I'm so married to my existing tmux workflows and layout that I'm not sure whether I'd ever feel open to trying out something like this. At the same time, orchestrating multiple agents with native tmux and git worktree does feel cumbersome.

Second this. BetterMouse supports hoards of features and only charges a one-time fee.

I imagined someone at Anthropic prompted "improve app performance", and this was the result.

Was reading this and thought the same thing.

I liked that the post is self-aware that it's promoting its own product. But the writing seemed more focus on the philosophy behind code reviews and the impact of AI, and less on the mechanics of how greptile differs from competitors. I was hoping to see more on the latter.

I'm not surprised. Lower barrier of entry -- thanks to AI in this case -- often leads to a decrease in quality in most things.

I have an almost identical setup with tmux and Tailscale and Termius, except I'd leave my laptop on and connect my phone to it instead: https://www.qu8n.com/posts/running-claude-code-from-my-phone