""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."
Embed this episode
Chapters
- 3:09 How "Careful Bootstrapped Alignment" might work
- 6:41 Some reasons this is hard
- 9:26 Why is this particularly important/time-sensitive?
- 9:42 Considerations from the High Reliability Organization literature, and the healthcare industry
- 12:27 Considerations from Bio-lab Safety Practices
- 13:33 Why in "top 3 priorities" instead of "top 7?"
- 15:19 Takeaways
- 16:46 Chat with me?
- 17:31 Related reading
No transcript yet.