Related papers: What do model reports say about their ChemBio benc…

In reaction to growing concerns about the potential harms of artificial intelligence (AI), societies have begun to demand more transparency about how AI models and systems are created and used. To address these concerns, several efforts…

The recent development of powerful AI systems has highlighted the need for robust risk management frameworks in the AI industry. Although companies have begun to implement safety frameworks, current approaches often lack the systematic…

The potential for rapidly-evolving frontier artificial intelligence (AI) models, especially large language models (LLMs), to facilitate bioterrorism or access to biological weapons has generated significant policy, academic, and public…

Recently, it has been found that frontier AI models can resist their own shutdown, a behavior known as self-preservation. We extend this concept to the behavior of resisting the shutdown of other models, which we call "peer-preservation."…

Frontier deep research agents (DRAs) plan a research task, synthesize across documents, and return a structured deliverable on demand. They are being deployed in enterprise workflows faster than they are being evaluated. Existing benchmarks…

This report provides a detailed comparison between the Safety and Security measures proposed in the EU AI Act's General-Purpose AI (GPAI) Code of Practice (Third Draft) and the current commitments and practices voluntarily adopted by…

Evaluating large language models (LLMs) for medical applications remains challenging due to benchmark saturation, limited data accessibility, and insufficient coverage of relevant tasks. Existing suites have either saturated, heavily depend…

Rapidly evolving AI exhibits increasingly strong autonomy and goal-directed capabilities, accompanied by derivative systemic risks that are more unpredictable, difficult to control, and potentially irreversible. However, current AI safety…

As artificial intelligence (AI) models are scaled up, new capabilities can emerge unintentionally and unpredictably, some of which might be dangerous. In response, dangerous capabilities evaluations have emerged as a new risk assessment…

Artificial Intelligence (AI) and Large Language Models (LLMs) have rapidly evolved in recent years, showcasing remarkable capabilities in natural language understanding and generation. However, these advancements also raise critical ethical…

As Artificial Intelligence (AI) systems proliferate, the need for systematic, transparent, and actionable processes for evaluating them is growing. While many resources exist to support AI evaluation, they have several limitations. Few…

Generative artificial intelligence (AI) offers numerous opportunities for research and innovation, but its commercialization has raised concerns about the transparency and safety of frontier AI models. Most models lack the necessary…

With the increasing integration of frontier large language models (LLMs) into society and the economy, decisions related to their training, deployment, and use have far-reaching implications. These decisions should not be left solely in the…

Leading language model (LM) providers like OpenAI and Anthropic allow customers to fine-tune frontier LMs for specific use cases. To prevent abuse, these providers apply filters to block fine-tuning on overtly harmful data. In this setting,…

Safety cases - clear, assessable arguments for the safety of a system in a given context - are a widely-used technique across various industries for showing a decision-maker (e.g. boards, customers, third parties) that a system is safe. In…

A spirited debate is taking place over the regulation of open foundation models: artificial intelligence models whose underlying architectures and parameters are made public and can be inspected, modified, and run by end users. Proposed…

Recent proposals for regulating frontier AI models have sparked concerns about the cost of safety regulation, and most such regulations have been shelved due to the safety-innovation tradeoff. This paper argues for an alternative regulatory…

This study examines how four prominent large language models (Claude 3.7 Sonnet, GPT-4o, Gemini 2.5 Flash, and Deepseek-V3) handle sexually oriented requests through qualitative content analysis. By evaluating responses to prompts ranging…

AI is undergoing a paradigm shift with the rise of models (e.g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks. We call these models foundation models to underscore their…

Hundreds of millions of people now regularly interact with large language models via chatbots. Model developers are eager to acquire new sources of high-quality training data as they race to improve model capabilities and win market share.…