Global Search

The Meta hack shows there’s more to AI security than Mythos

On June 5, 404 Media reported that attackers had been using Meta’s AI customer support agent to steal Instagram accounts. Their approach was simple: T...

Evolved Policy Gradients

We’re releasing an experimental metalearning approach called Evolved Policy Gradients, a method that evolves the loss function of learning agents, whi...

On first-order meta-learning algorithms

Reptile: A scalable meta-learning algorithm

We’ve developed a simple meta-learning algorithm called Reptile which works by repeatedly sampling a task, performing stochastic gradient descent on i...

Some considerations on learning to explore via meta-reinforcement learning