OpenAI's CBRN tests seem unclear
11/21/24 • 13 min
OpenAI says o1-preview can't meaningfully help novices make chemical and biological weapons. Their test results don’t clearly establish this.
https://planned-obsolescence.org/openais-cbrn-tests-seem-unclear
OpenAI says o1-preview can't meaningfully help novices make chemical and biological weapons. Their test results don’t clearly establish this.
https://planned-obsolescence.org/openais-cbrn-tests-seem-unclear
Previous Episode
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
If you like this episode you’ll love
Episode Comments
Generate a badge
Get a badge for your website that links back to this episode
<a href="https://goodpods.com/podcasts/ai-generated-audio-for-planned-obsolescence-259184/openais-cbrn-tests-seem-unclear-78772024"> <img src="https://storage.googleapis.com/goodpods-images-bucket/badges/generic-badge-1.svg" alt="listen to openai's cbrn tests seem unclear on goodpods" style="width: 225px" /> </a>
Copy