“One key aspect of intelligence is the ability to quickly learn how to perform a new task when given a brief instruction. For instance, a child may recognise real animals at the zoo after seeing a few pictures of the animals in a book, despite differences between the two. But for a typical visual model to learn a new task, it must be trained on tens of thousands of examples specifically labelled for that task.”
– DeepMind’s Flamingo, a single visual language model (VLM) that sets a new state of the art in few-shot learning on a wide range of open-ended multimodal tasks.
“The same network with the same weights can play Atari, caption images, chat, stack blocks with a real robot arm and much more, deciding based on its context whether to output text, joint torques, button presses, or other tokens.”
– DeepMind’s Gato works as a multi-modal, multi-task, multi-embodiment generalist agent.
Using symbolic regression to discover new science.
Ex-CEO of Sky on the future of the streaming model.
Sabine Hossenfelder on how to make a black hole. [YouTube]
Elon Musk explains updates to Starship And Starbase. [YouTube]