Skip to content
Featured on Startup Fame
Back to all stories
TNW | Artificial-intelligence

OpenAI lets Apollo embed six AI safety testers during training

The testers will check if OpenAI's models try to dodge their own safety controls.

By TNW | Artificial-intelligence

Excerpt shared by Lazyfounder

·Excerpt
OpenAI lets Apollo embed six AI safety testers during training
Image: Credit: Andrew Neel on Unsplash

Apollo Research will place six evaluators inside OpenAI for four months to check whether its models try to undermine alignment and control measures during training, testing and internal use. OpenAI controls staff access and can redact some evidence, but cannot hide Apollo’s verdicts or withhold material just because it is unfavourable.

AI safety group Apollo Research will place six of its evaluators inside OpenAI for four…

Continue reading on TNW | Artificial-intelligence ↗

Courtesy

This story was originally published by TNW | Artificial-intelligence. All rights belong to the original publisher.

Read the original on thenextweb.com ↗
Lazy Founder - Powered by Blogy.in

Contact us

Have a story tip, correction or partnership idea?

Write to us at tarun.kumar@blogy.in or talk to the founder directly. We read every message.

Contact us