CascadiaPrime Cognition

 Home    About    Blog    Future of Life Institute    Oxford FHI    Cambridge Center for Existential Risk   Machine Intelligence Research Institute     US Brain Project    EU Brain Project     China Brain Project  

 Blue Brain Project    EU Cognition Network   AAAI    CAIAC     Allen Institute for AI     AI for the Brain     AI 100     Center for Brains, Minds & Machines    Lifeboat     Long Now     PMD     AI International  


CascadiaPrime Cognition - Artificial Intelligence Safety Design

Artificial Intelligence Design lies at the heart of ensuring that humanity benefits from the emergence of beyond human intelligence and risks are mitigated.

This is a field at the very earliest stage and the links here therefore contain often just seeds of ideas. Intelligence appears to emerge from the ability of the brain to create successively higher levels of abstraction from data received from the world and to prune those abstractions based on new evidence - a precursor of the scientific method.

Some argue that the emergence of beyond human intelligence could emerge in an explosion like event while others contend that the process is more likely to be incremental. Some argue that this event will occur within a few decades, some argue that it will occur within a century and some argue it will not occur at all.

What is clear is that supra-national resources are currently being applied to reverse engineering the brain and creating computational resources that rival the brain's processing capacity.

  Microsoft shares open source system for training drones, other gadgets to move safely on their own (February 15, 2017)
  AI is getting smarter; Microsoft researchers want to ensure itís also getting more accurate (February 3, 2017)
  Nate Soares (MIRI): "Ensuring Smarter-than-Human Intelligence has a Positive Outcome" | Talks at Google (January 4, 2017)
  Brain motive modules interact: Selfishness and Altruism (March 3, 2016)
  Infusing Advanced AGIs with Human-Like Value Systems: Two Theses, Ben Goertzel, Chairman, Novamente LLC (February 2016)
  Roman V. Yampolskiy - Taxonomy of Pathways to Dangerous AI (November 2015)
  Nick Bostrom draft paper on value porosity and utility diversification (January 2015)
  Luke Muehlhauser - How to study superintelligence strategy (July 2014)
  Steve Omohundro - The Safe-AI Scaffolding Strategy is a positive way forward (February 2013)
  Microsoft bug testing software (June 2014)
  A3 - Self-Repairing Software Tackles Malware (November 2014)
  What could we do about intelligence explosion? Daniel Dewey slides, May 2014
  AAAI Asilomar Study on Long-Term AI Futures
  Collaborative learning Algorithm (June 2014)
  Model of human reasoning in the brain's prefrontal cortex (June 2014)
  Ray Kurzweil Biologically inspired models of intelligence - see 32min mark (June 2014)
  Abnormalities of brain structure and function associated with persistent violent behavior (January 2015)
  Mapping the maternal brain
  Eric Drexler: Exploring strategies for safe access to superintelligent problem-solving capabilities (2015)
  See Also the Artificial Intelligence Section of Cascadiaprime
  See Also the Artificial General Intelligence Section of Cascadiaprime
  See Also the Quantum Computing Revolution Section of Cascadiaprime