AXRP - the AI X-risk Research Podcast cover image

17 - Training for Very High Reliability with Daniel Ziegler

AXRP - the AI X-risk Research Podcast

CHAPTER

Is There a Violence in Alice in Wonderland?

There's a lot of alec's rider fenfick out there. The real metric that we care about, if we're valuading the system as a whole, sort of cares more about prompts that are more likely to be to producea completions that have an injury. Col: How often does your classifier give false negatives on totally random, randoml sampled snipbets? O, yes, interesting how i didn't know such a popular franchise, but in fact, there's a lot  of alec’s rider fanfick. Ah, so this was pretty biased towards it. Even that wasn't literally everything we trained on.

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