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 …

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 …

In reinforcement learning from human feedback, it is common to optimize against a reward
model trained to predict human preferences. Because the reward model is an imperfect …

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 …

With Artificial Intelligence (AI) increasingly permeating various aspects of society, including
healthcare, the adoption of the Transformers neural network architecture is rapidly changing …

An important aspect in developing language models that interact with humans is aligning
their behavior to be useful and unharmful for their human users. This is usually achieved by …

Widely used alignment techniques, such as reinforcement learning from human feedback
(RLHF), rely on the ability of humans to supervise model behavior-for example, to evaluate …

Generative AI has taken the world by storm, kicked off for real by ChatGPT and quickly
followed by further development and the release of GPT-4 and similar models from OpenAI's …