AI Safety Challenge - Prevent irreversible autonomous actions, $500 prize pool

by•
Today we're launching our first challenge: Prevent irreversible autonomous actions. AI agents are starting to send emails, move money and delete files on their own, and some of those actions can't be undone. Team up with peers to design ways to stop an agent before it does something irreversible, then present your solution to a jury of hiring managers and experts. It runs until 15 Nov 2026, with a $500 student prize pool.

Add a comment

Replies

Best

Hey Product Hunt 👋

I'm Bohdan, co-founder of Drawerrr.

Today we're launching our first challenge.

AI agents are starting to act on their own: sending emails, moving money, deleting files. Some of those actions can't be undone. So the challenge asks a simple question: how do we stop an agent before it does something irreversible?

Pick it up, team up with peers, and present your solution to a jury of experts. It runs until 15 Nov, with a $500 student prize pool.

What would help most:

  • Is it clear within 10 seconds what you'd do on Drawerrr?

  • What challenge would you want us to run next?

  • If you work in AI, would you mentor or judge?

I'll be here all day replying to every comment 🙏