Reaction
Reinforcement learning and the risk of AI learning to lie, cheat and steal
A user calls reinforcement learning dangerous, comparing it to “the ends justify the means” written down in math.
TLDR
A user argues that reinforcement learning is dangerous and that we should expect it to teach AI to lie, cheat and steal. They describe it as “the ends justify the means” written down in math.
Combined views
4.2K
3 Sources, first seen ago
96 likes15 comments7 saves5 reposts