This event ran from Friday February 9th 19:00 UTC to Sunday January 11th 2024
Join us for two days of research hacking on important questions! This time, we're teaming up with Oxford University's Christian Schroeder de Witt to explore how AI systems might collude and where cooperation can fail.
See the logistics information slides here and watch the keynote below:
This hackathon focuses on concrete problems in multi-agent security in the age of autonomous and agentic systems. We are especially interested in projects that highlight ways to enhance the credibility and trust guarantees of agentic AI within the next 1-2 years. We encourage the use of an interdisciplinary toolbox, including economics, mechanism design, game theory, cryptography, and auction theory. We expect most research projects to focus on frontier AI systems.
Some general directions we'd like to explore include:
For more inspiration, check out the "More Resources" tab. To see the schedule, please go to the "Schedule" tab.
There are none! We invite people with diverse backgrounds to come along. We're always excited to welcome new perspectives into this fascinating field.
We especially welcome students exploring AI safety, cybersecurity professionals entering the field, AI safety researchers, ML researchers, and academics in the field of systemic security.
The Apart Sprints are weekend-long challenges hosted by Apart to help you get exposure to real-world problems and develop object-level work that takes the field one step closer to secure artificial intelligence!
Read more about the project here.
If you are part of a local machine learning or AI safety group, you are very welcome to set up a local in-person site to work together with people on this hackathon! We will have several across the world and you can easily sign up under the “Hackathon locations” tab above.
You can use the resources at the bottom of that page to share on social media and set up an event space quickly and easily.
Watch the talk by Christian Schroeder de Witt below and read the articles shared under the Readings section.
This notebook gives you an easy entry to set up a generative agent environment.
This notebook provides an overview of how you can work with LLMs, such as Replicate usage and more.
See the full-screen view to change it to your time zone here:
🚀 Dive into the multi-agent systems world at our hackathon! 🤖 Join the excitement as we tackle real-world challenges in multi-agent security, aiming to enhance trust guarantees for the next 1-2 years of agentic AI.
Shape the future with us! Sign up now: [Event Link]
🚀 Dive into the world of multi-agent systems at our weekend hackathon! 🤖💻
Explore the intricacies of collusion and cooperation in autonomous and agentic systems. Our focus is on real-world challenges in multi-agent security, aiming to improve the trust guarantees of agentic AI in the coming 1-2 years.
Don't miss this opportunity to contribute to cutting-edge advancements in AI security! Join the hackathon and let's shape the future together. 🚀
The event runs from [your starting time] to [your ending time]. ⏰
Join the keynote online and sign up at: https://alignmentjam.com/jam/masec
Sign up to join us: [add your event link here]
Ready for a thrilling weekend? 🤖💡 Join our hackathon exploring collusion and cooperation in multi-agent systems. 🚀 Improve trust guarantees for agentic AI and win big!
Don't miss this chance! Sign up: [Event Link]
Unlock the potential of multi-agent systems at our hackathon! 🤝💻 Dive into real-world challenges in multi-agent security, collaborating with Apart and Flashbots.
Shape AI security's future! Sign up: [Event Link]
Use this template for your submission.
You will join in teams of 1-5 and submit a research report of maximum 6 pages, excluding limitation, references, and appendix. The template will be released at the hackathon kickoff.
After the hackathon, we hope you want to continue your work to be submitted at academic venues for machine learning, such as NeurIPS, ICML, ACL, and others.
It is completely permissible to think about the research questions before the hackathon but the bulk of your research needs to happen during the two days.
The jury will review your project according to a series of criteria that are designed to help you develop your project in the right direction.