Highlights: #158 – Holden Karnofsky on how AIs might take over even if they’re no smarter than humans, and his four-part playbook for AI risk from 80k After Hours

80k After Hours

The 80,000 Hours team

Highlights: #158 – Holden Karnofsky on how AIs might take over even if they’re no smarter than humans, and his four-part playbook for AI risk

23 minutes Posted Oct 6, 2023 at 8:45 pm.

Intro

Explosively fast progress

AI population explosion

Misaligned AI might not kill us all, and aligned AI could be catastrophic

Getting the AIs to do our alignment homework for us

The value of having a successful and careful AI lab

Why information security is so important

Holden vs hardcore utilitarianism

0:00

23:59

Download MP3

Share at current time

Show notes

This is a selection of highlights from episode #158 of The 80,000 Hours Podcast.

These aren't necessarily the most important, or even most entertaining parts of the interview — and if you enjoy this, we strongly recommend checking out the full episode:

Holden Karnofsky on how AIs might take over even if they’re no smarter than humans, and his four-part playbook for AI risk

And if you're finding these highlights episodes valuable, please let us know by emailing [email protected].

Highlights put together by Simon Monsour and Milo McGuire

← See all 109 episodes of 80k After Hours