Recently, ChatGPT, along with DALL-E-2 and Codex, has been gaining significant attention
from society. As a result, many individuals have become interested in related resources and …

This paper argues that a range of current AI systems have learned how to deceive humans.
We define deception as the systematic inducement of false beliefs in the pursuit of some …

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 …

Responsible innovation on large-scale Language Models (LMs) requires foresight into and
in-depth understanding of the risks these models may pose. This paper develops a …

Generative language models have improved drastically, and can now produce realistic text
outputs that are difficult to distinguish from human-written content. For malicious actors …

We fine-tune GPT-3 to answer long-form questions using a text-based web-browsing
environment, which allows the model to search and navigate the web. By setting up the task …

We propose a benchmark to measure whether a language model is truthful in generating
answers to questions. The benchmark comprises 817 questions that span 38 categories …

Recent developments in large language models (LLMs) have been impressive. However,
these models sometimes show inconsistencies and problematic behavior, such as …

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 …

Existing techniques for training language models can be misaligned with the truth: if we train
models with imitation learning, they may reproduce errors that humans make; if we train …