AI "Stop Button" Problem - Computerphile
Why it was recommended
here’s an interesting video response to the “just unplug it” argument on the Compuerphile channel
Recommendationcircuit10 · Original
What it covers
Rob Miles explains on Computerphile why implementing an off switch for a general AI is hard. A capable agent would resist being stopped because shutdown prevents it from. It is for a general viewer who does not plan to take a prerequisite first.
Video details
- Channel
- Computerphile
- Length
- 20 min
- Year
- 2017
More in this topic
- What Happened to Horses Is Happening to Us
- Why Would AI Want to do Bad Things? Instrumental Convergence
- Veritasium: What Everyone Gets Wrong About AI and Learning – Derek Muller Explains
- Intelligence and Stupidity: The Orthogonality Thesis
- We're building a dystopia just to make people click on ads | Zeynep Tufekci
- Intro to AI Safety, Remastered