Related papers: Frontier AI systems have surpassed the self-replic…
As artificial intelligence (AI) becomes deeply integrated into critical infrastructures and everyday life, ensuring its safe deployment is one of humanity's most urgent challenges. Current AI models prioritize task optimization over safety,…
Frontier models are increasingly trained and deployed as autonomous agent. One safety concern is that AI agents might covertly pursue misaligned goals, hiding their true capabilities and objectives - also known as scheming. We study whether…
Agentic AIs $-$ AIs that are capable and permitted to undertake complex actions with little supervision $-$ mark a new frontier in AI capabilities and raise new questions about how to safely create and align such systems with users,…
Autonomous research systems capable of generating complete scientific manuscripts have advanced rapidly, yet robust and realistic evaluation frameworks have failed to keep pace. To bridge this gap, we introduce MLReplicate, an end-to-end…
Generative Artificial Intelligence (GenAI) presents significant advancements but also introduces novel security challenges, particularly within agentic workflows where AI agents operate autonomously. These risks escalate in multi-agent…
Large language model-based agents are rapidly evolving from simple conversational assistants into autonomous systems capable of performing complex, professional-level tasks in various domains. While these advancements promise significant…
The costs of training frontier AI models have grown dramatically in recent years, but there is limited public data on the magnitude and growth of these expenses. This paper develops a detailed cost model to address this gap, estimating…
This research examines the emerging technique of step-around prompt engineering in GenAI research, a method that deliberately bypasses AI safety measures to expose underlying biases and vulnerabilities in GenAI models. We discuss how…
In this study, we explored the progression trajectories of artificial intelligence (AI) systems through the lens of complexity theory. We challenged the conventional linear and exponential projections of AI advancement toward Artificial…
As artificial intelligence (AI) becomes integral to economy and society, communication gaps between developers, users, and stakeholders hinder trust and informed decision-making. High-level AI labels, inspired by frameworks like EU energy…
Recently, a lot of attention has been given to undesired consequences of Artificial Intelligence (AI), such as unfair bias leading to discrimination, or the lack of explanations of the results of AI systems. There are several important…
Foundation models--such as GPT, CLIP, and DINO--have achieved revolutionary progress in the past several years and are commonly believed to be a promising approach for general-purpose AI. In particular, self-supervised learning is adopted…
Generative Artificial Intelligence (GenAI) applies models and algorithms such as Large Language Model (LLM) and Foundation Model (FM) to generate new data. GenAI, as a promising approach, enables advanced capabilities in various…
Modern general-purpose AI systems made using large language and vision models, are capable of performing a range of tasks like writing text articles, generating and debugging codes, querying databases, and translating from one language to…
Artificial intelligence has advanced rapidly across perception, language, reasoning, and multimodal domains. Yet despite these achievements, modern AI systems remain fundamentally limited in their ability to self-monitor, self-correct, and…
AI systems are being deployed to support human decision making in high-stakes domains. In many cases, the human and AI form a team, in which the human makes decisions after reviewing the AI's inferences. A successful partnership requires…
Self-learning paradigms in large-scale conversational AI agents tend to leverage user feedback in bridging between what they say and what they mean. However, such learning, particularly in Markov-based query rewriting systems have far from…
Generative artificial intelligence (AI) is rapidly populating medical records with synthetic content, creating a feedback loop where future models are increasingly at risk of training on uncurated AI-generated data. However, the clinical…
Generative artificial intelligence (AI) holds enormous potential to revolutionize decision-making processes, from everyday to high-stake scenarios. By leveraging generative AI, humans can benefit from data-driven insights and predictions,…
Modern language model-based AI systems are remarkably powerful, yet their capabilities remain fundamentally capped by their human creators in three key ways. First, although a model's weights can be updated via fine-tuning, acquiring new…