The reinforcement gap — or why some AI skills improve faster than others

AI tasks that work well with reinforcement learning are getting better fast — and threatening to leave the rest of the industry behind.

AI Agents, LLMs & Economic Growth : Karpathy’s Surprising Predictions

Discover Andrej Karpathy's insights on AI agents, LLMs, and economic growth. Insights on memory, education, and economic ...
Communications of the ACM

Shields for Safe Reinforcement Learning

Evaluating the advantages and potential drawbacks of shielding as a method for safe RL. Bettina Könighofer is an assistant ...

Nvidia researchers boost LLMs reasoning skills by getting them to 'think' during pre-training

By teaching models to reason during foundational training, the verifier-free method aims to reduce logical errors and boost ...
NextBigFuture

Looking at Current AI Learning Frameworks to Create Learning Pipelines to Achieve Superintelligence

Andrej Karpathy says that reinforcement learning is still terrible but better than all other AI learning approaches. Elon ...

The challenge of creating brains in a lab

They’re growing miniature 3D brains from stem cells. These aren’t your fictional mad scientists’ brains in a vat; they’re ...
Nature

Reinforcement learning improves behaviour from evaluative feedback

Reinforcement-learning algorithms 1,2 are inspired by our understanding of decision making in humans and other animals in which learning is supervised through the use of reward signals in response to ...