We should be spending less time proving today’s AIs are safe and more time figuring out how to tell if tomorrow’s AIs are dangerous: planned-obsolescence.org/dangerous-capability-tests-should-be-harder

We should be spending less time proving today’s AIs are safe and more time figuring out how to tell if tomorrow’s AIs are dangerous: planned-obsolescence.org/dangerous-capability-tests-should-be-harder

Dangerous capability tests should be harder

Thinking ahead to a future where AI decides everything <a href="https://www.planned-obsolescence.org?utm_medium=podcast">www.planned-obsolescence.org</a>

Technology

Thinking ahead to a future where AI decides everything www.planned-obsolescence.org

Thinking ahead to a future where AI decides everything <a href="https://www.planned-obsolescence.org?utm_medium=podcast" rel="noopener noreferrer">www.planned-obsolescence.org</a>

Share Dangerous capability tests should be harder

Sign up to save your podcasts

Dangerous capability tests should be harder

Dangerous capability tests should be harder

More shows like AI-Generated Audio for Planned Obsolescence

Making Sense with Sam Harris

Pivot

Pod Save America

The Daily

Up First from NPR

Hard Fork

AXRP - the AI X-risk Research Podcast

The Ezra Klein Show

LessWrong (Curated & Popular)

On with Kara Swisher