Our work

CAIS conducts research, field-building, and advocacy projects to reduce AI risk

We pursue impactful, technical AI safety research

Field-Building Projects

CAIS builds infrastructure and new pathways into AI safety

Compute Cluster

CAIS provides compute resources for AI/ML safety projects

Resources

Deeper-dive examinations of relevant AI safety topics

The AI Safety Newsletter

Regular briefings on the latest developments in AI safety, policy, and industry

2024 Impact Report

2023 Impact Report

Our Work

Field-Building Projects

Compute Cluster

Resources

AI Safety Newsletter

2024 Impact Report

2023 Impact Report

AI Risk Contact Careers Donate

CAIS 2024 Impact Report

CAIS 2024 Impact Report

This Hacker Team Is Bulletproofing AI Models For Companies Like OpenAI And Anthropic

Sarah Emerson

—

Oct 29, 2024

Read the article

CAIS is an AI safety non-profit. Our mission is to reduce societal-scale risks from artificial intelligence.

Our Work

View All Work Statement on AI Risk Field Building CAIS Research Compute Cluster Philosophy Fellowship CAIS Blog

Our Mission

About Us CAIS Media Annual Impact Report Frequently Asked Questions Learn About AI Risk Terms of Service Privacy Policy

Get involved

Donate Contact Us Careers

[email protected]

[email protected]

Cookies Notice:
This website uses cookies to identify pages that are being used most frequently. This helps us analyze data about web page traffic and improve our website. We only use this information for the purpose of statistical analysis and then the data is removed from the system. We do not and will never sell user data. Read more about our cookie policy on our privacy policy. Please contact us if you have any questions.

© 2025 Center for AI Safety

Website by Osborn Design Works