Skip to content

Source paper

GPT-4 Technical Report

OpenAI
arXiv 2303.08774 · 20237 upvotes on Hugging Face

Research ideas from this paper (4)

Generated by AI. The paper’s authors did not write these.

AI summary

This report details the development of GPT-4, a large-scale multimodal Transformer model that exhibits human-level performance on various professional benchmarks, such as the Uniform Bar Exam. The authors emphasize the use of predictable scaling laws to estimate model performance from smaller compute budgets and employ Reinforcement Learning from Human Feedback (RLHF) alongside Rule-Based Reward Models (RBRMs) to align the model with safety guidelines.

How it works (AI summary)

The model uses a Transformer-based architecture pre-trained on a massive corpus of text and image data to predict the next token. This is followed by a post-training alignment phase using Reinforcement Learning from Human Feedback (RLHF) and auxiliary Rule-Based Reward Models (RBRMs) to steer the model towards helpfulness and safety.