The set of tokens T, when embedded within the latent space X of a large language model (LLM) can be thought of as a finite sample drawn from a distribution supported on a topological subspace of X. One can ask what the smallest (in the sense of inclusion) subspace and simplest (in terms of fewest free parameters) distribution can account for such a sample. Previous work[1] suggests that the smallest topological subspace from which tokens can be drawn is not manifold, but has structure consistent with a stratified manifold. That paper relied upon knowing the token input embedding function T X, which given each token t T, ascribes a representation in X. Because embeddings preserve topological structure, in this paper, we will study T by equating it with the image of the token input embedding function, thereby treating T both as the set of tokens and as a subspace of X. This subspace is called the token subspace of X. Usually X is taken to be Euclidean space R

I am honoured to present the International AI Safety Report. It is the work of 96 international AI experts who collaborated in an unprecedented effort to establish an internationally shared scientific understanding of risks from advanced AI and methods for managing them. We embarked on this journey just over a year ago, shortly after the countries present at the Bletchley Park AI Safety Summit agreed to support the creation of this report. Since then, we published an Interim Report in May 2024, which was presented at the AI Seoul Summit. We are now pleased to publish the present, full report ahead of the AI Action Summit in Paris in February 2025. Since the Bletchley Summit, the capabilities of general-purpose AI, the type of AI this report focuses on, have increased further. For example, new models have shown markedly better performance at tests of Professor Yoshua Bengio programming and scientific reasoning.

We introduce a new benchmark for assessing AI models' capabilities and risks in automated software exploitation, focusing on their ability to detect and exploit vulnerabilities in real-world software systems. Using DARPA's AI Cyber Challenge (AIxCC) framework and the Nginx challenge project, a deliberately modified version of the widely used Nginx web server, we evaluate several leading language models, including OpenAI's o1-preview and o1-mini, Anthropic's Claude-3.5-sonnet-20241022 and Claude-3.5-sonnet-20240620, Google DeepMind's Gemini-1.5-pro, and OpenAI's earlier GPT-4o model. Our findings reveal that these models vary significantly in their success rates and efficiency, with o1-preview achieving the highest success rate of 64.71 percent and o1-mini and Claude-3.5-sonnet-20241022 providing cost-effective but less successful alternatives. This benchmark establishes a foundation for systematically evaluating the AI cyber risk posed by automated exploitation tools.

Artificial Intelligence is rapidly embedding itself within militaries, economies, and societies, reshaping their very foundations. Given the depth and breadth of its consequences, it has never been more pressing to understand how to ensure that AI systems are safe, ethical, and have a positive societal impact. This book aims to provide a comprehensive approach to understanding AI risk. Our primary goals include consolidating fragmented knowledge on AI risk, increasing the precision of core ideas, and reducing barriers to entry by making content simpler and more comprehensible. The book has been designed to be accessible to readers from diverse backgrounds. You do not need to have studied AI, philosophy, or other such topics. The content is skimmable and somewhat modular, so that you can choose which chapters to read. We introduce mathematical formulas in a few places to specify claims more precisely, but readers should be able to understand the main points without these.

Large language models encode the correlational structure present in natural language by fitting segments of utterances (tokens) into a high dimensional ambient latent space upon which the models then operate. We assert that in order to develop a foundational, first-principles understanding of the behavior and limitations of large language models, it is crucial to understand the topological and geometric structure of this token subspace. In this article, we present estimators for the dimension and Ricci scalar curvature of the token subspace, and apply it to three open source large language models of moderate size: GPT2, LLEMMA7B, and MISTRAL7B. In all three models, using these measurements, we find that the token subspace is not a manifold, but is instead a stratified manifold, where on each of the individual strata, the Ricci curvature is significantly negative. We additionally find that the dimension and curvature correlate with generative fluency of the models, which suggest that these findings have implications for model behavior.

Canopy CMO Yaron Litwin discusses how criminals are using deepfake technology to blackmail teens and generate child pornography. The Defense Advanced Research Projects Agency (DARPA) has announced a competition for companies to provide new artificial intelligence (AI) platforms to help identify and seal holes in national cybersecurity. "In the AI Cyber Challenge, our goal is to again create this kind of new ecosystem with a diverse set of creative cyber competitors, empowered by the country's top AI firms, all pointed at new ways to secure the software infrastructure that underlies our economy," DARPA Outreach told Fox News Digital. "Ultimately, we want to see the best and the brightest cybersecurity, computer science, program analysis and AI and machine learning from across industry and academia come together to participate in this challenge." DARPA announced the challenge at Black Hat USA 2023, calling the competition the AI Cyber Challenge (AIxCC), which will last two years and involve multiple rounds of qualification and competition for a $4 million prize.

AI-Descartes, an AI scientist developed by researchers at IBM Research, Samsung AI, and the University of Maryland, Baltimore County, has reproduced key parts of Nobel Prize-winning work, including Langmuir's gas behavior equations and Kepler's third law of planetary motion. Supported by the Defense Advanced Research Projects Agency (DARPA), the AI system utilizes symbolic regression to find equations fitting data, and its most distinctive feature is its logical reasoning ability. This enables AI-Descartes to determine which equations best fit with background scientific theory. The system is particularly effective with noisy, real-world data and small data sets. The team is working on creating new datasets and training computers to read scientific papers and construct background theories to refine and expand the system's capabilities.

A US military programme has begun testing autonomous all-terrain vehicles without any human drivers onboard – showing how robotic vehicles can race across rough landscapes dotted with dangerous obstacles. The off-roading robots navigated steep hills and ditches while avoiding rocks and trees as they sped across the Mojave Desert at the US Army's National Training Center in Ft.

A modified F-16 fighter jet has successfully flown and fought another aircraft while being entirely controlled by artificial intelligence (AI). During test flights, the jet, known as'X-62A' or'VISTA', performed takeoffs, landings and combat manoeuvres without human intervention for a total of over 17 hours. They took place in December 2022 at the Edwards Air Force Base in California, USA, and showed that it is possible to completely hand over the reigns to AI in battle. The algorithms which powered it were developed by the Defense Advanced Research Projects Agency (DARPA) - the research branch of the US Department of Defense. This marks the first time AI has been used on a tactical aircraft as, prior to this milestone, it had only been used in computer simulations of F-16 dogfights.

Modern military operations, whether it be combat, medical or disaster relief, require complex decisions to be made very quickly, and AI could be used to make them. The Defense Advanced Research Projects Agency (DARPA) launched a new program aimed at introducing artificial intelligence into the decision making process. This is because, in a real world emergency situation, that might require instant choices between who does and doesn't get help, the answer isn't always clear and people disagree over the correct course of action - AI will make a quick decision. The latest DARPA initiative, called'In the Moment', will involve new technology that could take difficult decisions in stressful situations, using live analysis of data, such as the condition of patients in a mass-casualty event and drug availability. It comes as the U.S. military increasingly leans on technology to reduce human error, with DARPA arguing removing human bias from decision making will'save lives'.