I'm Advait, a junior at UIUC majoring in Math and CS. I do AI research. I'm working towards a future where AI is safe and aligned.

I've worked on adversarial attacks with Prof. Haohan Wang, which resulted in InfoFlood. Our work was covered by 404 Media, POLITICO, IT Brew, and more. Recently, I spent the summer at MATS, where I worked on multi-agent system risks with Oliver Sourbut and Sid Black.

You can reach me at [email protected], or send anonymous feedback here.