Skip to content
""Carefully Bootstrapped Alignment" is organizationally hard" by Raemon episode artwork

Mar 21, 2023 19 min

""Carefully Bootstrapped Alignment" is organizationally hard" by Raemon

from LessWrong (Curated & Popular) Hosted by LessWrong

https://www.lesswrong.com/posts/thkAtqoQwN6DtaiGT/carefully-bootstrapped-alignment-is-organizationally-hard In addition to technical challenges, plans to safely develop AI face lots of organizational challenges. If you're running an AI lab, you need a concrete plan for handling that. In this post, I'll explore some of those issues, using one particular AI plan as an example. I first heard this described by Buck at EA Global London, and more recently with OpenAI's alignment plan. (I think Anthropic's plan has a fairly different ontology, although it still ultimately routes through a similar set of difficulties) I'd call the cluster of plans similar to this "Carefully Bootstrapped Alignment."

Episode details come from the podcast's RSS feed.

Embed this episode

Ready to play

""Carefully Bootstrapped Alignment" is organizationally hard" by Raemon

0:00 19:30

Chapters

  1. 3:09 How "Careful Bootstrapped Alignment" might work
  2. 6:41 Some reasons this is hard
  3. 9:26 Why is this particularly important/time-sensitive?
  4. 9:42 Considerations from the High Reliability Organization literature, and the healthcare industry
  5. 12:27 Considerations from Bio-lab Safety Practices
  6. 13:33 Why in "top 3 priorities" instead of "top 7?"
  7. 15:19 Takeaways
  8. 16:46 Chat with me?
  9. 17:31 Related reading

No transcript yet.

Requests help us decide what to transcribe next.

Frequently asked questions

How long is this episode of LessWrong (Curated & Popular)?

This episode is 19 minutes long.

When was this LessWrong (Curated & Popular) episode published?

This episode was published on March 21, 2023.

Can I download this LessWrong (Curated & Popular) episode?

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