Posts in category: Deepmind

We want to build safe, aligned artificial general intelligence (AGI) systems that pursue the intended goals of its designers. Causal influence diagrams (CIDs) are a way to model decision-making situations that allow us to reason about agent incentives. By relating training setups to the incentives that shape agent behaviour, CIDs help illuminate potential risks before training an agent and can inspire better agent designs. But how do we know when a CID is an accurate model of a training setup?Read More

We want to build safe, aligned artificial general intelligence (AGI) systems that pursue the intended goals of its designers. Causal influence diagrams (CIDs) are a way to model decision-making situations that allow us to reason about agent incentives. By relating training setups to the incentives that shape agent behaviour, CIDs help illuminate potential risks before training an agent and can inspire better agent designs. But how do we know when a CID is an accurate model of a training setup?Read More

Meet Edgar Duéñez-Guzmán, a research engineer on our Multi-Agent Research team who’s drawing on knowledge of game theory, computer science, and social evolution to get AI agents working better together.Read More

Meet Edgar Duéñez-Guzmán, a research engineer on our Multi-Agent Research team who’s drawing on knowledge of game theory, computer science, and social evolution to get AI agents working better together.Read More

Accelerating the search for life saving leishmaniasis treatmentsRead More

Looking into a protein’s past to unlock the mysteries of life itselfRead More

New insights into immunity to help protect the world’s floraRead More

Big data that leads to discoveries that benefit everyoneRead More

Researchers are designing more effective drugs than ever beforeRead More

Helping plastics become 100% recyclableRead More