New Funding Category Open in Foresight's AI Safety Grants

post by Allison Duettmann (allison-duettmann) · 2024-11-06T22:59:41.065Z · LW · GW · 0 comments

Contents

    2. Neurotech to integrate with or compete against AGI
    3. Security technologies for securing AI systems
    4. Safe multipolar human AI scenarios
  Application Process
None
No comments

Foresight Institute's AI Safety Grants Program added a new focus area in response to the continually evolving field. Moving forward, our funding ($1.5M-$2M annually) will be allocated across the following four focus areas:

 

1. Automating AI-relevant research and forecasting

• Scaling AI-enabled research to support safe AGI development
• Scaling efficient forecasting methods relevant for safe AGI
• Other approaches in this area

 

2. Neurotech to integrate with or compete against AGI

• Brain Computer Interfaces (BCI) to enhance human cognition or facilitate human-AGI collaboration
• Whole Brain Emulations (WBE) which might function as human-like general intelligences that are more interpretable and alignable than AGI
• Lo-fi emulations using behavioral and neural data with deep learning, potentially offering a cost-effective alternative to full WBEs
• Other approaches in this area

 

3. Security technologies for securing AI systems

• Implementations of computer security techniques (including POLA, SeL4-inspired systems, and hardened hardware security) to safeguard AI systems
• Automated red-teaming for AI security and capabilities
• Cryptographic and related techniques to enable trustworthy coordination architectures
• Other concrete approaches in this area

 

4. Safe multipolar human AI scenarios

• Game theory that addresses interactions between multiple humans, AIs, or ultimate AGIs
• Avoiding collusion and deception and/or encouraging pareto-preferred/positive-sum dynamics
• Approaches for addressing principal-agent problems in multi-agent systems
• Other concrete approaches in this area

 

Application Process

We accept applications on a quarterly cycle, with deadlines at the end of March, June, September, and December. Decisions are made within 8 weeks of each deadline.

Next Deadline: December 31st, 2024.

For more information and to apply: https://foresight.org/ai-safety

0 comments

Comments sorted by top scores.