AI Weekly Malaysia

Back to items Summaries

Learning complex goals with iterated amplification

ID
911
Status
new
Published
22 Oct 2018, 3:00 PM
Fetched
27 Jun 2026, 7:47 PM
Provider
OpenAI News
Category
ai-labs
Original URL
https://openai.com/index/learning-complex-goals-with-iterated-amplification
Source URL
https://openai.com/news/rss.xml

Excerpt

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.

Summary

No summary yet. It will appear after the daemon summarizes this item.

Top