Research Papers

• 
  Mar 17, 2023March 17, 2023

  GPTs are GPTs: An early look at the labor market impact potential of large language models

  Responsible AI

  Read paper
• 
  Mar 14, 2023March 14, 2023

  GPT-4

  Language

  Read paper
• 
  Jan 11, 2023January 11, 2023

  Forecasting potential misuses of language models for disinformation campaigns and how to reduce risk

  Safety & Alignment, Language

  Read paper
• 
  Dec 16, 2022December 16, 2022

  Point-E: A system for generating 3D point clouds from complex prompts

  Computer vision

  Read paper
• 
  Oct 19, 2022October 19, 2022

  Scaling laws for reward model overoptimization

  Reinforcement learning, Human feedback

  Read paper
• 
  Sep 21, 2022September 21, 2022

  Introducing Whisper

  Speech recognition, Transformers, Open source

  Read paper
• 
  Jul 28, 2022July 28, 2022

  Efficient training of language models to fill in the middle

  Language

  Read paper
• 
  Jul 25, 2022July 25, 2022

  A hazard analysis framework for code synthesis large language models

  Language, Safety & Alignment

  Read paper
• 
  Jun 28, 2022June 28, 2022

  DALL·E 2 pre-training mitigations

  Image generation, Responsible AI
• 
  Jun 23, 2022June 23, 2022

  Learning to play Minecraft with Video PreTraining

  Games, Representation learning, Reinforcement learning, Community

  Read paper
• 
  Jun 17, 2022June 17, 2022

  Evolution through large models

  Language

  Read paper
• 
  Jun 13, 2022June 13, 2022

  AI-written critiques help humans notice flaws

  Language, Human feedback, Safety & Alignment, Summarization

  Read paper
• 
  Jun 9, 2022June 9, 2022

  Techniques for training large neural networks

  Compute, Software engineering
• 
  May 28, 2022May 28, 2022

  Teaching models to express their uncertainty in words

  Language

  Read paper
• 
  Apr 13, 2022April 13, 2022

  Hierarchical text-conditional image generation with CLIP latents

  Image generation, Transformers, Generative models

  Read paper
• 
  Apr 13, 2022April 13, 2022

  Measuring Goodhart’s law

  Safety & Alignment
• 
  Mar 3, 2022March 3, 2022

  A research agenda for assessing the economic impacts of code generation models

  Community

  Read paper
• 
  Mar 3, 2022March 3, 2022

  Lessons learned on language model safety and misuse

  Safety & Alignment, Language, Responsible AI
• 
  Feb 2, 2022February 2, 2022

  Solving (some) formal math olympiad problems

  Language, Reasoning, Transformers

  Read paper
• 
  Jan 27, 2022January 27, 2022

  Aligning language models to follow instructions

  Language, Human feedback, Safety & Alignment, Responsible AI

  Read paper