Difference between revisions of "Hard takeoff"
m (→External Links) |
|||
| Line 15: | Line 15: | ||
==External Links== | ==External Links== | ||
| − | *[http://www.acceleratingfuture.com/michael/blog/2011/05/hard-takeoff-sources/ | + | *[http://www.acceleratingfuture.com/michael/blog/2011/05/hard-takeoff-sources/ Extensive Hard takeoff Resources] from Accelerating Future |
==See Also== | ==See Also== | ||
Revision as of 20:35, 12 June 2012
A hard takeoff refers to the creation of an AGI in a matter of minutes, hours or days. This scenario is widely considered much more precarious than a “soft takeoff”, due to the possibility of an AGI behaving in unexpected ways (ie. Unfriendly AI) with less opportunity to intervene before damage was done. As long as a system had adequate hardware the AGI would also rapidly accelerate into a SAI.
The feasibility of “hard takeoff” has been addressed by Hugo de Garis, Eliezer Yudkowsky, Ben Goertzel, Nick Bostrom and Michael Anissimov. However, there remains debate over whether a “hard takeoff” engineering strategy should be adopted due to the possible risks involved.
Although several science fiction authors have speculated that an AGI “hard takeoff” may happen by accident - for example, “The Internet waking-up” - this opinion is largely dismissed by computer scientist as intelligence is considered to be a hard problem.
Blog Posts
- Hard Takeoff by Eliezer Yudkowsky
- The Age of Virtuous Machines by J Storrs Hall President of The Foresight Institute
- Hard takeoff Hypothesis by Ben Goertzel.
External Links
- Extensive Hard takeoff Resources from Accelerating Future
