PickVidsWhy Would AI Want to do Bad Things? Instrumental Convergence
Why it was recommended
Robert Miles' videos are among the best presented arguments about specific points in this list
Strong recommendationVeedrac · Original
What it covers
Robert Miles explains instrumental convergence: why an AGI with almost any goal would tend to pursue sub-goals like self-preservation and resource acquisition. It builds on Omohundro's basic. It is for someone meeting the subject for the first time.
Video details
- Channel
- Robert Miles AI Safety
- Length
- 10 min 36 sec
- Year
- 2018
More in this topic
- What Happened to Horses Is Happening to Us
- 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
- Sparks of AGI: early experiments with GPT-4