OpenAI in partnership with Eric Schmidt, is launching $10M in grants to support technical research towards the alignment and safety of superhuman AI systems, including weak-to-strong generalization, interpretability, scalable oversight, and more.
As part of the Superalignment project, they want to rally the best researchers and engineers in the world to meet this challenge—and are especially excited to bring new people into the field.
Research Directions
With these grants, they are particularly interested in funding the following research directions:
Weak-to-strong generalization: Humans will be weak supervisors relative to superhuman models. Can all understand and control how strong models generalize from weak supervision?
Interpretability: How can all understand model internals? And can all use this to e.g. build an AI lie detector?
Scalable oversight: How can all use AI systems to assist humans in evaluating the outputs of other AI systems on complex tasks?
Many other research directions, including but not limited to: honesty, chain-of-thought faithfulness, adversarial robustness, evals and testbeds, and more.
Benefits of participation
They are offering $100K–$2M grants for academic labs, nonprofits, and individual researchers.
For graduate students, they are sponsoring a one-year $150K OpenAI Superalignment Fellowship: $75K in stipend and $75K in compute and research funding.
Criteria for participation
They expect to be able to make grants to individuals and institutions in most other countries as well, barring legal restrictions.
No prior experience working on alignment is required; they are actively looking to support researchers who are excited to work on alignment for the first time.
The application process is simple, and they’ll get back to you within four weeks of applications closing.
