AI Safety: Constitutional AI vs Human Feedback episode artwork

EPISODE · Jun 17, 2024 · 16 MIN

AI Safety: Constitutional AI vs Human Feedback

from Super Prompt: Generative AI · host Tony Wan

With great power comes great responsibility. How do leading AI companies implement safety and ethics as language models scale? OpenAI uses Model Spec combined with RLHF (Reinforcement Learning from Human Feedback). Anthropic uses Constitutional AI. The technical approaches to maximizing usefulness while minimizing harm. Solo episode on AI alignment.REFERENCEOpenAI Model Spechttps://cdn.openai.com/spec/model-spec-2024-05-08.html#overviewAnthropic Constitutional AIhttps://www.anthropic.com/news/claudes-constitutionTo stay in touch, sign up for our newsletter at https://superprompt.substack.com

Episode metadata supplied by the publisher feed · Published Jun 17, 2024

Embed this episode

Ready to play

AI Safety: Constitutional AI vs Human Feedback

0:00 16:38

No transcript for this episode yet

We transcribe on demand. Request one and we'll notify you when it's ready — usually under 10 minutes.

No similar episodes found.

Frequently Asked Questions

How long is this episode of Super Prompt: Generative AI?

This episode is 16 minutes long.

When was this Super Prompt: Generative AI episode published?

This episode was published on June 17, 2024.

Can I download this Super Prompt: Generative AI episode?

Yes. Use the download control on the episode player to save the publisher-provided media file.
URL copied to clipboard!