research
∙
09/21/2023
The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"
We expose a surprising failure of generalization in auto-regressive larg...
share
research
∙
09/01/2023
Taken out of context: On measuring situational awareness in LLMs
We aim to better understand the emergence of `situational awareness' in ...
research
∙
06/30/2022
Forecasting Future World Events with Neural Networks
Forecasting future world events is a challenging but valuable task. Fore...
research
∙
05/28/2022
Teaching Models to Express Their Uncertainty in Words
We show that a GPT-3 model can learn to express uncertainty about its ow...
research
∙
10/13/2021
Truthful AI: Developing and governing AI that does not lie
In many contexts, lying – the use of verbal falsehoods to deceive – is h...
research
∙
09/08/2021
TruthfulQA: Measuring How Models Mimic Human Falsehoods
We propose a benchmark to measure whether a language model is truthful i...
research
∙
11/13/2020
Active Reinforcement Learning: Observing Rewards at a Cost
Active reinforcement learning (ARL) is a variant on reinforcement learni...
research
∙
11/16/2019
Sensory Optimization: Neural Networks as a Model for Understanding and Creating Art
This article is about the cognitive science of visual art. Artists creat...
research
∙
07/02/2019
Generalizing from a few environments in safety-critical reinforcement learning
Before deploying autonomous agents in the real world, we need to be conf...
research
∙
03/13/2018
Active Reinforcement Learning with Monte-Carlo Tree Search
Active Reinforcement Learning (ARL) is a twist on RL where the agent obs...
research
∙
02/20/2018
The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation
This report surveys the landscape of potential security threats from mal...
research
∙
07/17/2017
Trial without Error: Towards Safe Reinforcement Learning via Human Intervention
AI systems are increasingly applied to complex tasks that involve intera...
research
∙
05/24/2017
When Will AI Exceed Human Performance? Evidence from AI Experts
Advances in artificial intelligence (AI) will transform modern life by r...
research
∙
01/15/2017
Agent-Agnostic Human-in-the-Loop Reinforcement Learning
Providing Reinforcement Learning agents with expert advice can dramatica...
research
∙
12/18/2015