We believe superintelligence could arrive within the next 10 years. These AI systems would have vast capabilities—they could be hugely beneficial, but also potentially pose large risks.
Today, we align AI systems to ensure they are safe using reinforcement learning from human feedback (RLHF). However, aligning future superhuman AI systems will pose fundamentally new and qualitatively different technical challenges.
Superhuman AI systems will be capable of complex and creative behaviors that humans cannot fully understand. For example, if a superhuman model generates a million lines of extremely complicated code, humans will not be able to reliably evaluate whether the code is safe or dangerous to execute. Existing alignment techniques like RLHF that rely on human supervision may no longer be sufficient. This leads to the fundamental challenge: how can humans steer and trust AI systems much smarter than them?
This is one of the most important unsolved technical problems in the world. But we think it is solvable with a concerted effort. There are many promising approaches and exciting directions, with lots of low-hanging fruit. We think there is an enormous opportunity for the ML research community and individual researchers to make major progress on this problem today.
Benefits
- 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.
Requirements
With these grants, we are particularly interested in funding the following research directions:
- Weak-to-strong generalization: Humans will be weak supervisors relative to superhuman models. Can we understand and control how strong models generalize from weak supervision?Â
- Interpretability: How can we understand model internals? And can we use this to e.g. build an AI lie detector?
- Scalable oversight: How can we 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.
Method of Application
Click Here to Apply
- 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.
For More Information,
Application Deadline: February 18, 2024.
