FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT.
TED | What happens when our computers get smarter than we are? | Nick Bostrom | 27 APRIL 2015
TED | How civilization could destroy itself — and 4 ways we could prevent it | Nick Bostrom | 17 Jan 2020
Superintelligence: Paths, Dangers, Strategies by Nick Bostrom
Bostrom categorises four (4) control methods for safe containment of Superintelligent AI:
1. Boxing – restricted access to the outside world by Superintelligent AI
2. Incentivising – using social or technical rewards for Superintelligent AI
3. Stunting – constraints on cognitive abilities of Superintelligent AI
4. Tripwires – detection of activity beyond expected behaviour automatically closes down the Superintelligent AI system
Note: Since 2014, AI technology has developed faster than scientists expected: The current prediction for superintelligent machines is between 2025 and 2030 (if it has not happened already and we don’t know about it)
Scientific Consensus: Mathematically provable safe deployments of Superintelligent AI is a requirement for the future survival of the human race.