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 early stages and we have only completed experiments on simple toy algorithmic domains, we’ve decided to present it in its preliminary state because we think it could prove to be a scalable approach to AI safety.
Related Posts
Our approach to AI safety
Ensuring that AI systems are built, deployed, and used safely is critical to our mission.
Operation “A2Z”: Multilingual influence activity
OpenAI banned “A2Z” accounts using AI to generate multilingual influence content about elections, Ukraine, and politics across platforms.
Developers can now submit apps to ChatGPT
Developers can now submit apps for review and publication in ChatGPT, with approved apps appearing in a new in-product directory…
