Announcing Atlas Computing — LessWrong
Atlas Computing is a new nonprofit working to collaboratively advance AI capabilities that are asymmetrically risk-reducing. Our work consists of building scoped prototypes and creating an ecosystem around @davidad’s Safeguarded AI programme at ARIA (formerly referred to as the Open Agency Architecture). We formed in Oct 2023, and raised nearly $1M, primarily from the Survival and Flourishing Fund and Protocol Labs. We have no physical office, and are currently only Evan Miyazono (CEO) and Daniel Windham (software lead), but over the coming months and years, we hope to create compelling evidence that: We think that, in addition to encoding human values into AI systems, a very complementary way to dramatically reduce AI risk is to create external safeguards that limit AI outputs. Users (individuals, groups, or institutions) should have tools to create specifications that list baseline safety requirements (if not full desiderata for AI system outputs) and also interrogate those specifi
x Announcing Atlas Computing — LessWrong AI Governance AI Risk Atlas Computing Open Agency Architecture Project Announcement AI Personal Blog 45 Announcing Atlas Computing by miyazono 11th Apr 2024 5 min read 4 45 Atlas Computing is a new nonprofit working to collaboratively advance AI capabilities that are asymmetrically risk-reducing. Our work consists of building scoped prototypes and creating an ecosystem around @davidad ’s Safeguarded AI programme at ARIA (formerly referred to as the Open Agency Architecture). We formed in Oct 2023, and raised nearly $1M, primarily from the Survival and F
saved by
related reading
- Amazon to invest up to $4 billion in Anthropic AI. What to know about the startup. | Voxvox.com
- Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
- Your Solution Doesn't Know Your Problem Existsblog.atlascomputing.org
- Project Glasswing: Securing critical software for the AI era \ Anthropicanthropic.com
- The case for ensuring that powerful AIs are controlled — LessWronglesswrong.com
- The Case Against AI Control Research — LessWronglesswrong.com
- Core views on AI safety: When, why, what, and how \ Anthropicanthropic.com
- AI Control: Improving Safety Despite Intentional Subversion — LessWronglesswrong.com
- A basic systems architecture for AI agents that do autonomous research — LessWronglesswrong.com
- Ten AI safety projects I'd like people to work onthirdthing.ai
- Sequent: Scale and Automation for Higher Confidence in Alignment — Sequentsequent.org
- AI safety undervalues founders — LessWronglesswrong.com