Browsing: Center for AI Safety
The White House Executive Order on Artificial Intelligence highlights the risks of large language models (LLMs) empowering malicious actors in…
A new paper co-authored by the former CEO of Google has outlined a future where AI training data centers could…
Cybersecurity and cyberattacks cost hundreds of billions of dollars annually.1 Rapid progress in AI will dramatically increase the stakes.In the…
A new paper co-authored by the former CEO of Google has outlined a future where AI training data centers could…
This is the second post in a sequence of posts that describe our models for Pragmatic AI Safety. The internal…
A new paper co-authored by the former CEO of Google has outlined a future where AI training data centers could…
Reading the minds of LLMsInterpreting and controlling models has long been a significant challenge. Our research ‘Representation Engineering: A Top-Down…
A new paper co-authored by the former CEO of Google has outlined a future where AI training data centers could…
The blog post below is partly adapted from the book’s preface.We are excited to announce the launch of AI Safety,…
A new paper co-authored by the former CEO of Google has outlined a future where AI training data centers could…