We build AI agents to find vulnerabilities in other AI agents. The playground started as an internal tool that we used to test our own offensive agent Nyx.
But we realised that hacking an AI is about have as wide a distribution of attacks as possible, especially those which aren't in the distribution of the models. So we are launching playground as a platform to crowdsource agent jailbreaks.
And although hacking AI is super fun and we are sure people will do it for free, we want to reward those who help us push forward the offensive frontier of AI. So we are committing $100K in prizes over the next 12 months (starting with $2K for the first week long challenge), which is kinda a lot for a startup!
The playground is open source. Happy hacking!!
Comments URL: [https://news.ycombinator.com/item?id=48895849](https://news.ycombinator.com/item?id=48895849)
Points: 1