I'm 13 and built an OpenAI o1-like AI model – would love your feedback

I’m Hayden, a 13-year-old developer, and I’ve built a CoT logical thinking and reasoning AI model similar to OpenAI o1.

It's powered by open source small models like Llama 3.1 and 3.2 and I would love for you to try it and share your feedback with me.

You can try it here: https://ai.pixelverse.tech/app/cortexchat

I built it just for fun and launched it a day after the o1 release. It's not perfect yet but its still amazing to see how a detailed prompt can have such a difference on the quality of the LLM response!

Please let me know any feedback or suggestions! Thank you!

(read more info here: https://ai.pixelverse.tech/t1)

Congratulations on the quality and the speed of the output! As a usual test for any LLM, I ask something I know a bit about, then check to make sure the answer jives. Your tools did a great job on both a literature and programming test.

The only issue I had was with the CSS for the UI, which is always a nightmare, I know. The reasoning steps did not have the proper classes applied and rendered strangely. Also, the prompt input box doesn't expand when you type more than fits on one line. But there are always early issues in any web UI -- so kudos, regardless.

As another commenter said, carry on and do great stuff!

All I got to say is I'm highly highly impressed if that 13-year-old claim is true. You could be using your own AI stuff to be polishing up your writing a little bit but even then the maturity that's on display here and the attitude you have is amazing.

Go on and do amazing things!