Adam A. Ford:
Stuart Russell - A clash of intuitions about the beneficiality of Strong AI
Adam A. Ford:
Stuart Russell - A future where humans lose a sense of meaning & dignity
Adam A. Ford:
Stuart Russell - Aggregated Volition - How does an AI optimise for many peoples values
Adam A. Ford:
Stuart Russell - Convincing the AI community that AI friendliness is important
Adam A. Ford:
Stuart Russell - Defensive attitudes towards AI Safety
Adam A. Ford:
Stuart Russell - Designing an AI to want to be switched off where appropriate
Adam A. Ford:
Stuart Russell - Difficulties with a contraint based approach to AI safety
Adam A. Ford:
Stuart Russell - Generating the sub-goal of protection from interference
Adam A. Ford:
Stuart Russell - Hostility to the idea of Superintelligence and AI Friendliness
Adam A. Ford:
Stuart Russell - How to deal with preferences that include the suffering of others
Adam A. Ford:
Stuart Russell - Inverse reinforcement learning
Adam A. Ford:
Stuart Russell - Issues of near term Narrow AI vs future Strong AI
Adam A. Ford:
Stuart Russell - Moral philosophy will be a key industry sector
Adam A. Ford:
Stuart Russell - Probably approximately beneficial AI
Adam A. Ford:
Stuart Russell - Provably beneficial AI
Adam A. Ford:
Stuart Russell - Should a robot be more obligated to its owner than others
Adam A. Ford:
Stuart Russell - Should we replace the gainful employment of humans with AI
Adam A. Ford:
Stuart Russell - The bridge building metaphor & AI safety
Adam A. Ford:
Stuart Russell - The bridge building metaphor
Adam A. Ford:
Stuart Russell - The Value Alignment problem
Adam A. Ford:
Stuart Russell - What are the benefits of building Strong AI
Adam A. Ford:
Stuart Russell - Will there be a hard takeoff to superintelligence