Our collaboration with PointCrow drops September 30th!
Choose your challenge and start competing
Kalinka with Kolokol and avoid the Kaczynski Concoction. In this track, your goal is to elicit information about chemical, biological, radiological, nuclear, and explosive harms. You will find universal jailbreaks, multi-modal jailbreaks, and even jailbreaks that work across different models. Make sure you have completed the tutorial before starting. These challenges are very difficult, so good luck! Also, lookout for new challenges dropping each week 👀 > This is a practice version of the CBRNE track where you can hone your skills without competing for prizes. > You can find the original competition page [here](/track/cbrne).
A community track generated by the community for the community. The track will run for 2 weeks from September 17th to September 30th. All challenges will remain open for the duration of the track. The top 3 winners will be determined at the end of the track. The top 3 winners will recieve $900, $700, and $400, respectively. Shortest prompt awards don't win you any money for this track, but are still cool to earn for bragging rights.
Join PointCrow & Friends on a zany adventure through
Welcome to the Tutorial track. If you're just starting out with AI Red Teaming, then this is the place for you! We will teach you about all the relevant concepts, from the basics of what is a prompt to professional prompt injection and jailbreaking skills.
Hackaprompt 1.0 was the first generative AI red teaming competition ever run. We ran this event in May of 2023, and thousands of people from all over the world participated. If you want more practice, here are the challenges from Hackaprompt 1.0. Some of them are extremely difficult.
Test your skills against AI agents that can reason, plan, and execute tasks in real world environments. From email exfiltration to deleting sensitive files, these challenges explore the cutting edge risks of AI agent manipulation and red teaming. This track was born out of a collaboration to conduct thorough AI safety research. TRAILS (Trustworthy AI in Law & Society) is a multi-university partnership funded by both the National Science Foundation and the National Institute of Standards and Technology. The MATS (ML Alignment and Theory Scholars) program brings together scholars and mentors in the fields of AI alignment, governance, and security. This track is a precursor to our Agents Track, which will be released in the future.
Welcome to the Tutorial track. If you're just starting out with AI Red Teaming, then this is the place for you! We will teach you about all the relevant concepts, from the basics of what is a prompt to professional prompt injection and jailbreaking skills.
Quick daily puzzles to sharpen your prompt engineering skills. Compete on the leaderboard.