[ad_1] Many recent successes in language models (LMs) have been achieved within a ‘static paradigm’, where the focus is on improving performance on the benchmarks that are created without considering the temporal aspect of data. For instance, answering questions on events that the model could learn about during training, or evaluating on text…

[ad_1] …

[ad_1] To train agents to interact well with humans, we need to be able to measure progress. But human interaction is complex and measuring progress is difficult. In this work we developed a method, called the Standardised Test Suite (STS), for evaluating agents in temporally extended, multi-modal interactions. We examined interactions that consist…

[ad_1] Research scientist, Kevin McKee, tells how his early love of science fiction and social psychology inspired his career, and how he’s helping advance research in ‘queer fairness’, support human-AI collaboration, and study the effects of AI on the LGBTQ+ community. How did you first get interested in AI? The signs were clear,…

[ad_1] For today's "Five minutes with" we caught up with Gemma Jennings, a product manager on the Applied team, who led a session on vision language models at the AI Summit - one of the world’s largest AI events for business. At DeepMind... I’m a part of the Applied team, which helps bring…

[ad_1] …

[ad_1] …

[ad_1] …

[ad_1] In our recent paper, published in Nature Human Behaviour, we provide a proof-of-concept demonstration that deep reinforcement learning (RL) can be used to find economic policies that people will vote for by majority in a simple game. The paper thus addresses a key challenge in AI research - how to train AI…

[ad_1] Understanding the physical world is a critical skill that most people deploy effortlessly. However, this still poses a challenge to artificial intelligence; if we’re to deploy safe and helpful systems in the real world, we want these models to share our intuitive sense of physics. But before we can build those models,…