research
∙
05/24/2023
Model evaluation for extreme risks
Current approaches to building general-purpose AI systems tend to produc...
share
research
∙
11/12/2022
Formalizing the presumption of independence
Mathematical proof aims to deliver confident conclusions, but a very sim...
research
∙
03/04/2022
Training language models to follow instructions with human feedback
Making language models bigger does not inherently make them better at fo...
research
∙
09/22/2021
Recursively Summarizing Books with Human Feedback
A major challenge for scaling machine learning is training models to per...
research
∙
09/02/2020
Learning to summarize from human feedback
As language models become more powerful, training and evaluation are inc...
research
∙
09/18/2019
Fine-Tuning Language Models from Human Preferences
Reward learning enables the application of reinforcement learning (RL) t...
research
∙
10/19/2018
Supervising strong learners by amplifying weak experts
Many real world learning tasks involve complex or hard-to-specify object...
research
∙
09/22/2018
Unrestricted Adversarial Examples
We introduce a two-player contest for evaluating the safety and robustne...
research
∙
05/02/2018
AI safety via debate
To make AI systems broadly useful for challenging real-world tasks, we n...
research
∙
04/02/2018
Certifiable Randomness from a Single Quantum Device
We give a protocol for producing certifiable randomness from a single un...
research
∙
06/12/2017
Deep reinforcement learning from human preferences
For sophisticated reinforcement learning (RL) systems to interact useful...
research
∙
11/11/2016
A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models
Generative adversarial networks (GANs) are a recently proposed class of ...
research
∙
10/11/2016
Transfer from Simulation to Real World through Learning Deep Inverse Dynamics Model
Developing control policies in simulation is often more practical and sa...
research
∙
06/21/2016
Concrete Problems in AI Safety
Rapid progress in machine learning and artificial intelligence (AI) has ...
research
∙
05/09/2016