Circuit analysis is a promising technique for understanding the
internal...
We present speculative sampling, an algorithm for accelerating transform...
Recent work has shown that asking language models to generate reasoning ...
Large language models are now part of a powerful new paradigm in machine...
We present Sparrow, an information-seeking dialogue agent trained to be ...
Large language models produce human-like text that drive a growing numbe...
Recent large language models often answer factual questions correctly. B...
Language models can learn a range of capabilities from unsupervised trai...
Language Models (LMs) often cannot be deployed because of their potentia...
We enhance auto-regressive language models by conditioning on document c...
This paper aims to help structure the risk landscape associated with
lar...
For artificial intelligence to be beneficial to humans the behaviour of ...
Reward learning enables the application of reinforcement learning (RL) t...
To solve complex real-world problems with reinforcement learning, we can...
To make AI systems broadly useful for challenging real-world tasks, we n...
Deep learning techniques lie at the heart of several significant AI adva...
We study the effectiveness of neural sequence models for premise selecti...
TensorFlow is an interface for expressing machine learning algorithms, a...