GPT-4 is a large-scale, multimodal model developed by OpenAI that can process both image and text inputs and generate text outputs. It exhibits human-level performance on various professional and academic benchmarks, including passing a simulated bar exam with a score around the top 10% of test takers. The model is a Transformer-based and pre-trained to predict the next token in a document. The post-training alignment process improves its performance on measures of factuality and adherence to desired behavior. The development of infrastructure and optimization methods that behave predictably across a wide range of scales was a core component of the project, allowing for accurate prediction of GPT-4's performance based on models trained with less compute. GPT-4 has the potential to be used in a wide range of applications such as dialogue systems, text summarization, and machine translation.
