
20 - 'Reform' AI Alignment with Scott Aaronson
AXRP - the AI X-risk Research Podcast
The Future of AI Risk
I think 10 years ago, I would not have imagined taking a year off from quantum computing to work on AI safety. And now, you know, here I am. So I think it should not be a stretch to say that my views will continue to evolve in response to, youknow, events. And that I see that as a good thing and not a bad thing. Right? As for what would make me more scared? I mean, the first time that we see an AI actually deceiving humans,. You know, copying itself over the internet, covering its tracks, things of that kind is going to change the whole discussion about AI risk. It's probably going to happen somewhere.
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.