Journey to Singularity
- Explainable / Interpretable AI
- Automated Learning
- Apprenticeship Learning - Inverse Reinforcement Learning (IRL)
- Reinforcement Learning (RL)
- Isaac Asimov's "Three Laws of Robotics"
- A robot may not injure a human being or, through inaction, allow a human being to come to harm.
- A robot must obey orders given it by human beings except where such orders would conflict with the First Law.
- A robot must protect its own existence as long as such protection does not conflict with the First or Second Law.
Autonomy Matrix (Levels)
- computer offers no assistance, humans make all decisions and take all actions
- computer offers a complete set of alternatives
- computer narrows the selection down to a few choices
- computer suggests one action
- computer executes that action if the human operator approves
- computer allows the human a restricted time to veto before automatic execution
- computer executes automatically then informs the human
- computer informs human after execution only if asked
- computer informs human after execution only if it decides to
- computer decides everything and acts fully autonomously
Stop Button Problem
- Defense Innovation Board seeks ‘off switch’ to keep rogue AI in check | Jory Heckman - Federal News Network