Misinformation such as fake news and rumors is a serious threat for information ecosystems
and public trust. The emergence of large language models (LLMs) has great potential to …

AI alignment aims to make AI systems behave in line with human intentions and values. As
AI systems grow more capable, the potential large-scale risks associated with misaligned AI …

We report the development of GPT-4, a large-scale, multimodal model which can accept
image and text inputs and produce text outputs. While less capable than humans in many …

Reinforcement learning from human feedback (RLHF) is a technique for training AI systems
to align with human goals. RLHF has emerged as the central method used to finetune state …

In this short consensus paper, we outline risks from upcoming, advanced AI systems. We
examine large-scale social harms and malicious uses, as well as an irreversible loss of …

Artificial intelligence (AI) is progressing rapidly, and companies are shifting their focus to
developing generalist AI systems that can autonomously act and pursue goals. Increases in …

External audits of AI systems are increasingly recognized as a key mechanism for AI
governance. The effectiveness of an audit, however, depends on the degree of access …

This work identifies 18 foundational challenges in assuring the alignment and safety of large
language models (LLMs). These challenges are organized into three different categories …

Manipulation is a concern in many domains, such as social media, advertising, and
chatbots. As AI systems mediate more of our digital interactions, it is important to understand …

Automated dialogue or conversational systems are anthropomorphised by developers and
personified by users. While a degree of anthropomorphism may be inevitable due to the …