Jan Leike
4 papers · Latest:
GPT-4 Technical Report
GPT-4 is a large-scale multimodal Transformer model achieving human-level performance on professional and academic benchmarks through advanced training and alignment techniques.
Training language models to follow instructions with human feedback
This paper presents InstructGPT, a method to align language models with user intent by fine-tuning GPT-3 using human feedback, resulting in more truthful, helpful, and less toxic outputs.
Evaluating Large Language Models Trained on Code
Codex, a GPT model fine-tuned on GitHub code, significantly outperforms prior models in generating correct Python programs from docstrings, demonstrating strong code synthesis capabilities.
Deep reinforcement learning from human preferences
This paper demonstrates that deep reinforcement learning agents can be effectively trained using human preferences as feedback instead of explicit reward functions, enabling complex task learning with minimal human input.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.