Center for AI Safety (CAIS) Blog

CAIS Blog | Center for AI Safety 
 

 

 

 
 AI risk Resources
 Contact Careers Donate Resources
 AI Risk Contact Careers Donate Careers Donate 
 
 

 CAIS Blog

 Deeper-dive examinations of relevant AI safety topics

 Thank you! Your submission has been received! Oops! Something went wrong while submitting the form. Press Release • Jun 23, 2025 • 2 min read Josué Estrada Joins Center for AI Safety as Chief Operating Officer

 

 Written by: AI Risks • Sep 15, 2024 • 2 min read Submit Your Toughest Questions for Humanity's Last Exam

 CAIS and Scale AI are excited to announce the launch of Humanity's Last Exam, a project aimed at measuring how close we are to achieving expert-level AI systems. The exam is aimed at building the world's most difficult public AI benchmark gathering experts across all fields. People who submit successful questions will be invited as coauthors on the paper for the dataset and have a chance to win money from a $500,000 prize pool.

 Written by: Dan Hendrycks, Alexandr Wang AI Risks • Sep 9, 2024 • 5 min read Superhuman Automated Forecasting

 This post describes a superhuman forecasting AI called FiveThirtyNine, which generates probabilistic predictions for any query by retrieving relevant information and reasoning through it. We explain how the system works, its performance compared to human forecasters, and its potential applications in improving decision-making and public discussions.

 Written by: Long Phan, Andrew Zeng, Mantas Mazeika, Adam Khoja, Dan Hendrycks AI Risks • May 10, 2024 • AI Safety, Ethics, and Society

 AI Safety, Ethics and Society is a textbook and online course providing a non-technical introduction to how current AI systems work, why many experts are concerned that continued advances in AI could pose severe societal-scale risks, and how society can manage and mitigate these risks.

 Written by: AI Risks • Apr 29, 2024 • 5 min read Representation Engineering: a New Way of Understanding Models

 Representation engineering is an exciting new field which explores how we can better understand traits like honesty, power seeking, and morality in LLMs. We show that these traits can be identified by looking at model activations, and these same traits can also be controlled. This method differs from mechanistic approaches which focus on bottom-up interpretations of node to node connections. In contrast, representation engineering looks at larger chunks of representations and higher-level mechanisms to understand models in a 'top-down' fashion.

 Written by: Izzy Barrass, Long Phan AI Risks • Apr 10, 2024 • 43 min read A Bird's Eye View of the ML Field

 The internal dynamics of the ML field are not immediately obvious to the casual observer. This post will present some important high-level points that are critical to beginning to understand the field, and is meant as background for our later posts.

 Written by: Dan Hendrycks Thomas Woodside AI Risks • Mar 6, 2025 • 9 min r

... (truncated, 5 KB total)