Story

I figured I'd jump into this great age of GenAI coding with Gemini CLI and Claude Code.

I created a small project to test things out and started asking questions (plus set up agents files). And frankly, I'm less than underwhelmed. Bugs galore, some making both these tools unusable (which is shocking, I'm fairly sure Claude Code was the first one and it's not Open Source, so Gemini CLI must be an independent reimplementation - but somehow they both seem to share the same bugs).

For example when I ask Claude Code a question on Ubuntu 24.04, if the answer is longer than about a full screen, I can't scroll up to see the entire answer. When I scroll up to see the answer, the Claude Code scrolls up ALL THE WAY TO THE TOP OF THE ENTIRE CONVERSATION, and I can't scroll down gradually. So I either see the first question and whatever fits in one screen-full of text or I see the bottom screen-full of text for the last question. No in-between. This makes Claude Code unusable since most answers are longer than a page.

Gemini CLI also suffers from silly scrolling bugs.

These are known issues, I've asked Gemini about both and it provided workarounds that mostly don't work.

I'm trying to use the CLI modes instead of TUI (claude -p "question here"...) but it's a lot more cumbersome. Plus I lose the immediate context for series of questions.

Is this the GenAI revolution? Am I holding it wrong? Is everyone vibe coding on Macs?

I'm fairly sure I have the latest versions for both CLIs and I swear I've seen better implemented TUIs from the 90s, before the 10x vibe coding revolution.

Now, don't get me wrong, they're both nice for exploring and definitely unlock lots of possibilities, but how can the tools themselves be so abysmal with so many billions invested into them?

I'd think both companies can afford top notch CLI/TUI tool developers - and DX is a sink-or-swim type of test for both tools.

Is OpenAI Codex any better?