AXRP - the AI X-risk Research Podcast cover image

22 - Shard Theory with Quintin Pope

AXRP - the AI X-risk Research Podcast

CHAPTER

The Benefits of Alignment Over Capabilities

Alignment generalizes much further than capabilities. If there's a gap in how well you can evaluate stuff then you're like more bottlenecked on alignment than you are on capabilities I don't so just like looking or comparing the capabilities that GPT for or I or other humans have versus like our ability to judge outcomes enabled by those that would be enabled if we had vastly greater capabilities I think alignment seems quite a bit ahead in my perspective. Once humans figured out how to build CRISPR they did not then figure out molecular nanotechnology from that. The degree to which this generalizes to other contexts is quite limited.

00:00
Transcript
Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
App store bannerPlay store banner