gerroo

I think AI for science is a good idea in its core, but academia really needs a way to "mark" AI generated papers. Maybe a better application of this would be in ML literature where experiments can be done with something like codex or claude code?

Cool idea, will try. Since it seems mostly llm generated you could publish the process and prompts for transparency.

Thanks for sharing this :)

Totally agree! How would you communicate this to the non-technicals in an influential way?

What did you use to make the demo video?

I built something similar for research papers (https://paperpilot.app). I like how clean the UI is :)

lool I wrote my IB extended essay on this. I had a caesar cipher instead though.

No shit

Absolutely amazing! When I was developing a chrome extension all I could think of was a severe lack of dev-tools. I'll try it when I get the opportunity.

Cool. Some points to improve

- It'd be nice to have some sort of devtools view or a way of copying / seeing the components directly on the website. Personally, I really like bit.dev's home page. You could do something similar. - I like that you focused on marketing blocks. It complements the shadcn blocks. - If you want to grow this, I think adding the ability add / edit blocks directly on the website would be nice. You could see everyone's blocks, upvote and discuss them.

These points aside, your blocks look great! Keep it up!

Thanks for that :)

Hey,

I took a look at https://figr.design/

How is it different from v0.dev?

I wholeheartedly agree. I'm trying to get involved with this project and thought that it was an effort in the right direction. Appreciate the insights.

If they let me I'll get to work on the "hard part."

Finally the intuit tax software monopoly can go away. Excited to see how it turns out.

I wonder how much they spent on it lol

That'd be so nice. Imagine executing the code for an ai paper and seeing the beautiful visualizations as you read it.

Do you know if there's a way to write latex comments in Zotero / Mendeley? It's something I've been looking for.

Yes! That's what I was thinking.

Evidence finding tasks improve reading retention (A Multidimensional Investigation of Deep-level and Surface-level Processing, Dinsmore & Alexander).

I made something that generates evidence finding tasks automatically for any (ideally something like history or social studies) research paper.

I'd love to have some feedback on it or advice on how to grow it.