This Challenge was posted 5 days ago

 

AlignGeist

Building Evaluations for AI Alignment (Safety) Research with the insights of the humanities

At this moment, the jobs in AI alignment (safety) research are almost entirely reserved for computer scientists and engineers. Relying on this very small group of people to both understand the complex technicalities of AI AND to contemplate the moral, creative, and social questions surrounding it is highly problematic. As the world is panicking about the future of AI, and safety researchers are quitting left and right, isn’t it time for more interdisciplinary, creative teams from the humanities to step in and help?

I am pitching AlignGeist as an independent research group/organization which develops AI alignment research and evaluation approaches with the expertise of the arts, psychology, history, philosophy, and other social sciences. This weekend we will design and run Evaluations which compare multiple LLMs. I envision exploring in particular LLMs' responses about the next developments in AI at the boundaries between digital and analog realities.

What questions could AlignGeist ask that the current field of AI alignment research struggles to approach? Let’s experiment together this weekend with forming a working concept!

👋 Carmiella Zorzi
All attendees, sponsors, partners, volunteers, and staff are required to abide by the Hack Code of Conduct. The organisers are committed to enforcing it throughout the event and expect everyone to contribute to creating a safe, respectful, and welcoming environment for all.

The contents of this website, unless otherwise stated, are licensed under a Creative Commons Attribution 4.0 International License. The application that powers this site is available under the MIT license.