Magnifying Glass
×
Join or Log in
Are.na
Sam Hart
Strong AI

Info

This channel appears in

×
Magnifying Glass
This mostly cites papers from Berkeley, Google Brain, DeepMind, and OpenAI from the past few years, because that work is most visible to me. I'm almost certainly missing stuff from older literature and other institutions, and for that I apologize - I'm just one guy, after all.

Deep Reinforcement Learning Doesn't...

Added by Sam Hart
Updated 10 months ago

Instrumental convergence suggests that an intelligent agent with apparently harmless goals can act in surprisingly harmful ways. For example, a computer with the sole goal of solving the Riemann hypothesis could attempt to turn the entire Earth into computronium in an effort to increase its computing power so that it can succeed in its calculations.

Instrumental convergence - Wikipedia

Added by Sam Hart
Updated a year ago

DFjy1KeV0AAmVH3.jpg

Added by Sam Hart
Updated a year ago

making ai less bad

  • by Francis Tseng
  • 49 blocks • a day ago

Strong AI, 2˚ ↕

Added by Sam Hart
Updated a year ago

Nothing here yet...

Go to Sam Hart's profile or explore recent public channels from other users