Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

For non-vibe coding purposes I've found that my $200 Claude (Claude Code) account regularly outperformed my $200 ChatGPT (Codex) account. This was after 2 months of heavily testing both mostly in Terminal TUI/CLI form and most recently with the latest VSCode/Cursor incarnations.

Even with the additional Sora usage and other bells & whistles that ChatGPT @ $200 provides, Claude provides more value for my use cases.

Claude Code is just a lot more comfortable being in your workflow and being a companion or going full 'agent(s)' and running for 30 minutes on one ticket. It's also a lot happier playing with Agents from other APIs.

There's nothing wrong with Anthropic wanting to completely own that segment and not have aspirations of world domination like OpenAI. I don't see how that's a negative.

If anything, the more ChatGPT becomes a 'everything app' the less likely I am to hold on to my $20 account after cancelling the $200 account. I'm finding the more it knows about me the more creeped out and "I didn't ask for this" I become.



> There's nothing wrong with Anthropic wanting to completely own that segment and not have aspirations of world domination

It's very clear by their actions (not words) that they are shooting for the moon in order to survive. There is no path to sustainability as a collection of dev tools.


Especially now that sama wants us to sext with ChatGPT




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: