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.
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.
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.
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.
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.
Advances in AI could increase the risk of cyberattacks, yet AI also promises to improve cyber defenses. A coordinated effort between technology and regulatory sectors is crucial for leveraging AI's potential to strengthen cyber defenses and address security shortcomings.
Metrics drive the ML field, but defining these metrics is difficult. Successful benchmarks aren't the inevitable result of annotating a large enough dataset. Instead, effective ML benchmarks produce clear evaluations, have minimal barriers to entry, and concretize an important phenomena.
Advances in AI and DNA synthesis promise to revolutionize medicine… but could enable bioterrorism. A thoughtful mix of public health measures and restricted access to advanced capabilities can manage this risk while also alleviating natural viral threats.
The Center for AI Safety state its support for the White House's securing of voluntary commitments from leading AI companies.