Answer to How quickly could an AI go from the first indications of problems to an unrecoverable disaster?

From Stampy's Wiki
Plex's Answer to How quickly could an AI go from the first indications of problems to an unrecoverable disaster? / (Redirected from Answer to How quickly could an AI go from the first indications of problems to an unrecoverable disaster?)

If the AI system was deceptively aligned (i.e. pretending to be nice until it was in control of the situation) or had been in stealth mode while getting things in place for a takeover, quite possibly within hours. We may get more warning with weaker systems, if the AGI does not feel at all threatened by us, or if a complex ecosystem of AI systems is built over time and we gradually lose control.

Paul Christiano writes a story of alignment failure which shows a relatively fast transition.

Answer to

Canonical Answer Info
(edits welcome)
Original by: plex (edits by stampy, Luca)


Discussion