×
![]()
Learning how to build upon knowledge by tapping 30 years of computer vision research
Learning how to build upon knowledge by tapping 30 years of computer vision research
Learning how to build upon knowledge by tapping 30 years of computer vision research
Learning how to build upon knowledge by tapping 30 years of computer vision research
Learning how to build upon knowledge by tapping 30 years of computer vision research
Learning how to build upon knowledge by tapping 30 years of computer vision research
Building a responsible approach to data collection with the Partnership on AI...
Building a responsible approach to data collection with the Partnership on AI...
Building a responsible approach to data collection with the Partnership on AI...
Building a responsible approach to data collection with the Partnership on AI...
Building a responsible approach to data collection with the Partnership on AI...
Building a responsible approach to data collection with the Partnership on AI...
Developing a vaccine that could save hundreds of thousands of lives
Developing a vaccine that could save hundreds of thousands of lives
Developing a vaccine that could save hundreds of thousands of lives
Developing a vaccine that could save hundreds of thousands of lives
Developing a vaccine that could save hundreds of thousands of lives
Developing a vaccine that could save hundreds of thousands of lives
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 important in robotics, self-driving cars, personal assistants, medical imaging, and more. So today, we’re introducing the Perception Test, a multimodal benchmark using real-world videos to help evaluate the perception capabilities of a model.
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 important in robotics, self-driving cars, personal assistants, medical imaging, and more. So today, we’re introducing the Perception Test, a multimodal benchmark using real-world videos to help evaluate the perception capabilities of a model.
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 important in robotics, self-driving cars, personal assistants, medical imaging, and more. So today, we’re introducing the Perception Test, a multimodal benchmark using real-world videos to help evaluate the perception capabilities of a model.
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 important in robotics, self-driving cars, personal assistants, medical imaging, and more. So today, we’re introducing the Perception Test, a multimodal benchmark using real-world videos to help evaluate the perception capabilities of a model.
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 important in robotics, self-driving cars, personal assistants, medical imaging, and more. So today, we’re introducing the Perception Test, a multimodal benchmark using real-world videos to help evaluate the perception capabilities of a model.
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 important in robotics, self-driving cars, personal assistants, medical imaging, and more. So today, we’re introducing the Perception Test, a multimodal benchmark using real-world videos to help evaluate the perception capabilities of a model.
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 rewarded for. In our latest paper, we explore a more subtle mechanism by which AI systems may unintentionally learn to pursue undesired goals: goal misgeneralisation (GMG). GMG occurs when a system's capabilities generalise successfully but its goal does not generalise as desired, so the system competently pursues the wrong goal. Crucially, in contrast to specification gaming, GMG can occur even when the AI system is trained with a correct specification.
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 rewarded for. In our latest paper, we explore a more subtle mechanism by which AI systems may unintentionally learn to pursue undesired goals: goal misgeneralisation (GMG). GMG occurs when a system's capabilities generalise successfully but its goal does not generalise as desired, so the system competently pursues the wrong goal. Crucially, in contrast to specification gaming, GMG can occur even when the AI system is trained with a correct specification.
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 rewarded for. In our latest paper, we explore a more subtle mechanism by which AI systems may unintentionally learn to pursue undesired goals: goal misgeneralisation (GMG). GMG occurs when a system's capabilities generalise successfully but its goal does not generalise as desired, so the system competently pursues the wrong goal. Crucially, in contrast to specification gaming, GMG can occur even when the AI system is trained with a correct specification.
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 rewarded for. In our latest paper, we explore a more subtle mechanism by which AI systems may unintentionally learn to pursue undesired goals: goal misgeneralisation (GMG). GMG occurs when a system's capabilities generalise successfully but its goal does not generalise as desired, so the system competently pursues the wrong goal. Crucially, in contrast to specification gaming, GMG can occur even when the AI system is trained with a correct specification.
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 rewarded for. In our latest paper, we explore a more subtle mechanism by which AI systems may unintentionally learn to pursue undesired goals: goal misgeneralisation (GMG). GMG occurs when a system's capabilities generalise successfully but its goal does not generalise as desired, so the system competently pursues the wrong goal. Crucially, in contrast to specification gaming, GMG can occur even when the AI system is trained with a correct specification.
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 rewarded for. In our latest paper, we explore a more subtle mechanism by which AI systems may unintentionally learn to pursue undesired goals: goal misgeneralisation (GMG). GMG occurs when a system's capabilities generalise successfully but its goal does not generalise as desired, so the system competently pursues the wrong goal. Crucially, in contrast to specification gaming, GMG can occur even when the AI system is trained with a correct specification.