
7 - Side Effects with Victoria Krakovna
AXRP - the AI X-risk Research Podcast
Do You Think That the Base Line Is a Problem in the Sarcastic Case?
In a deterministic environment, you can show that this method avoids interference. But in the sarcastic case, it actually doesn't quite work. So is thike your you want to compare to specific countrfactule supposed to like an average over countrefactuls? This is where it gets a bit messy, and i haven't been able to come up with a very satisfactory answer.
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.