Kapitelklicken springt direkt hin
Shownotes
Paul Christiano is the world’s leading AI safety researcher. My full episode with him is out!
We discuss:
- Does he regret inventing RLHF, and is alignment necessarily dual-use?
- Why he has relatively modest timelines (40% by 2040, 15% by 2030),
- What do we want post-AGI world to look like (do we want to keep gods enslaved forever)?
- Why he’s leading the push to get to labs develop responsible scaling policies, and what it would take to prevent an AI coup or bioweapon,
- His current research into a new proof system, and how this could solve alignment by explaining model's behavior
- and much more.
Watch on YouTube (youtu.be/9AAhTLa0dT0). Listen on Apple Podcasts (podcasts.apple.com/us/podcast/paul-christiano-…), Spotify (open.spotify.com/episode/5vOuxDP246IG4t4K3EuEK…), or any other podcast platform. Read the full transcript here (dwarkeshpatel.com/i/138448008/transcript). Follow me on Twitter (twitter.com/dwarkesh_sp) for updates on future episodes.
Open Philanthropy
Open Philanthropy is currently hiring for twenty-two different roles to reduce catastrophic risks from fast-moving advances in AI and biotechnology, including grantmaking, research, and operations.
For more information and to apply, please see the application (openphilanthropy.org/research/new-roles-on-our…): openphilanthropy.org/research/new-roles-on-our…
The deadline to apply is November 9th; make sure to check out those roles before they close.
Timestamps
() - What do we want post-AGI world to look like?
() - Timelines
() - Evolution vs gradient descent
() - Misalignment and takeover
() - Is alignment dual-use?
() - Responsible scaling policies
() - Paul’s alignment research
() - Will this revolutionize theoretical CS and math?
() - How Paul invented RLHF
() - Disagreements with Carl Shulman
() - Long TSMC but not NVIDIA
This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit dwarkesh.com?utm_medium=podcast&utm_campai…
