<span class="vcard">Google DeepMind Blog</span>
Google DeepMind Blog

Measuring perception in AI models

Perception – the process of experiencing the world through senses – is a significant part of intelligence. And building agents with human-level perceptual understanding of the world is a central but challenging task, which is becoming increasingly impo…

Measuring perception in AI models

Perception – the process of experiencing the world through senses – is a significant part of intelligence. And building agents with human-level perceptual understanding of the world is a central but challenging task, which is becoming increasingly impo…

Measuring perception in AI models

Perception – the process of experiencing the world through senses – is a significant part of intelligence. And building agents with human-level perceptual understanding of the world is a central but challenging task, which is becoming increasingly impo…

How undesired goals can arise with correct rewards

As we build increasingly advanced artificial intelligence (AI) systems, we want to make sure they don’t pursue undesired goals. Such behaviour in an AI agent is often the result of specification gaming – exploiting a poor choice of what they are reward…

How undesired goals can arise with correct rewards

As we build increasingly advanced artificial intelligence (AI) systems, we want to make sure they don’t pursue undesired goals. Such behaviour in an AI agent is often the result of specification gaming – exploiting a poor choice of what they are reward…

How undesired goals can arise with correct rewards

As we build increasingly advanced artificial intelligence (AI) systems, we want to make sure they don’t pursue undesired goals. Such behaviour in an AI agent is often the result of specification gaming – exploiting a poor choice of what they are reward…

How undesired goals can arise with correct rewards

As we build increasingly advanced artificial intelligence (AI) systems, we want to make sure they don’t pursue undesired goals. Such behaviour in an AI agent is often the result of specification gaming – exploiting a poor choice of what they are reward…

Discovering novel algorithms with AlphaTensor

In our paper, published today in Nature, we introduce AlphaTensor, the first artificial intelligence (AI) system for discovering novel, efficient, and provably correct algorithms for fundamental tasks such as matrix multiplication. This sheds light on …

Discovering novel algorithms with AlphaTensor

In our paper, published today in Nature, we introduce AlphaTensor, the first artificial intelligence (AI) system for discovering novel, efficient, and provably correct algorithms for fundamental tasks such as matrix multiplication. This sheds light on …

Discovering novel algorithms with AlphaTensor

In our paper, published today in Nature, we introduce AlphaTensor, the first artificial intelligence (AI) system for discovering novel, efficient, and provably correct algorithms for fundamental tasks such as matrix multiplication. This sheds light on …