Aggregator

Our approach to alignment research

OpenAI News
4 years 1 month ago
We are improving our AI systems’ ability to learn from human feedback and to assist humans at evaluating AI. Our goal is to build a sufficiently aligned AI system that can help us solve all other alignment problems.

Guess the size of an atomic bomb and an iOS supply chain attack

toooold
4 years 1 month ago
Disclaimer: Nothing in this blog is related to the author’s current day-to-day work. The content is neither affiliated nor sponsored by any companies. The story in this post is based on a true event that happened in two parts, six years apart, and is full of nostalgia.

Managed ad