Controllable AI for a Safer, More Ethical Future
Sun, Jul 16, 2023, 03:00 PM · 30:00
The text discusses the emergence of generative AIs and the risks associated with them, such as misinformation and value locking. It highlights the need for AI alignment, which aims to steer AI systems towards intended goals and ethical principles. The text also mentions OpenAI's plan for alignment and the challenges associated with it. It introduces the concept of controllable AI as an alternative to perfectly aligned AI, emphasizing the importance of being able to stop AI systems if needed. The text then delves into the open agency architecture, which aims to achieve controllability through a specification step and han evaluation. The challenges of building such a system are discussed, including the need for a new language for specifications and the complexity of designing a full world model. The text concludes by highlighting the urgency of addressing AI risks and the need for more time and safer design architectures.
No description
More from Funding the Commons Paris 2023
Artizen Fund x Funding the Commons: A Mechanism Design Experiment in Participatory Capital Allocation for Public Goods
Funding the Commons
Funding the Commons Paris 2023 · Jul 16, 2023
Artizen Fund
AI Extinction Risks: Challenges and Opportunities in Funding AI Safety
Funding the Commons
Funding the Commons Paris 2023 · Jul 16, 2023
Simeon Campos
Hypercerts: How to build modern impact funding systems
Funding the Commons
Funding the Commons Paris 2023 · Jul 16, 2023
Holke Brammer
GainForest: A Global Non-Profit To Help Fund Our Natural World With AI & Web3
Funding the Commons
Funding the Commons Paris 2023 · Jul 16, 2023
David Dao
Public Goods That Will Onboard the Next Billion
Funding the Commons
Funding the Commons Paris 2023 · Jul 16, 2023
Marek Olszewski, René Reinsberg
Data Provenance and the Climate Crisis
Funding the Commons
Funding the Commons Paris 2023 · Jul 16, 2023
Alan Ransil
Announcement: Ethereum Climate Platform
Funding the Commons
Funding the Commons Paris 2023 · Jul 16, 2023
Steven Haft
Nature Realms: Unleashing Community Power for Biodiversity Conservation
Funding the Commons
Funding the Commons Paris 2023 · Jul 16, 2023
Mallika Robinson
Invisible Hands, Tangible Solutions: Is Capitalism Really the Problem?
Funding the Commons
Funding the Commons Paris 2023 · Jul 16, 2023
Cassidy Daly, Jesse Pollak, Lucas Vogelsang
Retro Public Harms and Behavioral Game Theory solutions
Funding the Commons
Funding the Commons Paris 2023 · Jul 16, 2023
Matt Stephenson
Grants for (Public) Good: Establishing Resilient, Democratic Funding Mechanisms
Funding the Commons
Funding the Commons Paris 2023 · Jul 16, 2023
Megan Lister
What Money Can't Buy: The Limits of Ecosystem Funding
Funding the Commons
Funding the Commons Paris 2023 · Jul 16, 2023
Ori Applebaum