Large Language Models (LLMs) went from non-existent to ubiquitous in the machine
learning discourse within a few years. Due to the fast pace of the field, it is difficult to identify …

While artificial intelligence (AI) offers promising solutions in healthcare, it also poses a
number of threats to human health and well-being via social, political, economic and security …

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 …

Large language models are now tuned to align with the goals of their creators, namely to be"
helpful and harmless." These models should respond helpfully to user questions, but refuse …

For a long time, humanity has pursued artificial intelligence (AI) equivalent to or surpassing
the human level, with AI agents considered a promising vehicle for this pursuit. AI agents are …

Large generative AI models (LGAIMs), such as ChatGPT, GPT-4 or Stable Diffusion, are
rapidly transforming the way we communicate, illustrate, and create. However, AI regulation …

Through considerable effort and intuition, several recent works have reverse-engineered
nontrivial behaviors oftransformer models. This paper systematizes the mechanistic …

The advancement of artificial intelligence in education (AIED) has the potential to transform
the educational landscape and influence the role of all involved stakeholders. In recent …

We describe our early efforts to red team language models in order to simultaneously
discover, measure, and attempt to reduce their potentially harmful outputs. We make three …

Generative image modeling enables a wide range of applications but raises ethical
concerns about responsible deployment. This paper introduces an active strategy combining …