Yeah, spears usually wins first.

Sure, but it's more about whether the small model can find the vulnerability that bigger model can.

LMAO, I do genuinely believe it's much easier to hack right now. Just matter of timer sth blows up on the news.

Exactly! I think it might go deeper than that. Some issue or result of like hosting or configuration that it doesn't seem that all is just by looking at the code base. It's a combination of a lot of stuff.

Hi all,

I'm Kedan, a 3rd year CS PhD student at UIUC. We're just build a fashion shopping app that allows user to visualize any outfit, using cutting edge AI. We just launched today, thought you might be interested to take a look. Also, give us an upvote on Prodhunt! https://www.producthunt.com/posts/style-space-visualize-outf...

Nice work - is this an academic project or a Startup?

It started as academic research, but now thinking about building a product!

Thanks for answering the survey! Appreciated!

Not yet up. Will soon!

Thanks for taking it! Sorry that it's a bit long(50 questions). Should be doable within 8 minutes, if you're not struggling too hard.

Actually, didn't use adversarial loss.

That's about average performance among random population.