How AI Training Scales
We’ve discovered that the gradient noise scale, a simple statistical metric, predicts the parallelizability of neural network training.
Dario Amodei
Learning Complex Goals with Iterated Amplification
We’re proposing an AI safety technique called iterated amplification that lets us specify complicated behaviors and goals that are beyond human scale, by demonstrating how to decompose a task into simpler sub-tasks, rather than by providing labeled data or a reward function. Although this idea is in its very
AI and Compute
Since 2012, the amount of compute used in the largest AI training runs has been increasing exponentially with a 3.5 month doubling time (by comparison, Moore’s Law had an 18 month doubling period).
AI Safety via Debate
We’re proposing an AI safety technique which trains agents to debate topics with one another, using a human to judge who wins. We believe that this or a similar approach could eventually help us train AI systems to perform far more cognitively advanced tasks than humans are capable of, while
Preparing for Malicious Uses of AI
We’ve co-authored a paper that forecasts how malicious actors could misuse AI technology, and potential ways we can prevent and mitigate these threats. This paper is the outcome of almost a year of sustained work with our colleagues at the Future of Humanity Institute, the Centre for the Study of
Gathering Human Feedback
RL-Teacher is an open-source implementation of our interface to train AIs via occasional human feedback rather than hand-crafted reward functions. The underlying technique was developed as a step towards safe AI systems, but also applies to reinforcement learning problems with rewards that are hard to specify.
This simulated
Gathering Human Feedback
RL-Teacher is an open-source implementation of our interface to train AIs via occasional human feedback rather than hand-crafted reward functions. The underlying technique was developed as a step towards safe AI systems, but also applies to reinforcement learning problems with rewards that are hard to specify.
This simulated
Learning from Human Preferences
One step towards building safe AI systems is to remove the need for humans to write goal functions, since using a simple proxy for a complex goal, or getting the complex goal a bit wrong, can lead to undesirable and even dangerous behavior. In collaboration with DeepMind’s safety team, we’ve