Alright, here's a side-by-side comparison of OpenAI's new Codex vs Codebuff Codex took 5 minutes and didn't implement the client side of my request 😢 Codebuff took 1 minute and got it right! 🔥

Codebuff (YC F24) is the original coding CLI! We've been working on it for longer and it shows. It reads a dozen files instantly to solve your query better and faster. Try it now with free credits:

What happens when you combine every AI? It's time for something better than ChatGPT...

@CodebuffAI better "thinking" animation though

@CodebuffAI 🚀🚀🚀

@CodebuffAI Look at the source bud. It's no different than just prompting them in a web interface, no symbols, no indexing, nothing.

@CodebuffAI I’ll give it a try

@CodebuffAI It could also show visibility to the edits made

@CodebuffAI Which model was codebuffAI using, o4-mini?

@CodebuffAI It's using Sonnet 3.6 here. You can try it with o4-mini though by running: codebuff --model o4-mini

@CodebuffAI Why/how is codebuff better than codex?

@CodebuffAI Codebuff reads a bunch more files immediately, which helps it produce higher quality results and faster!

@CodebuffAI okay james but is it opensource? because codex can improve rapidly being oss

Just snagged the latest npm to try out the product. I burned through 500 credits in less than 4 minutes with nothing but simple UI fixes. If I purchased the Pro account for 5000 credits and vibe coded for 4 hours a day including weekends... 500 credits every 4 minutes for 4 hours a day, I would spend $8,820 per month at the given pricing rate Was cool to see it in action but not sure how this would ever be sustainable...am I doing it wrong? 🥲

Wow that's a lot of credits! I wouldn't say that is typical. We have prompt caching which should make it cheaper between messages but possibly something went wrong? If you could email [email protected] and let us know your accounts email address (via github login), that would be very helpful! Might be able to figure out why it cost so much for you.