News for hackers. Stuff that matters.
Re:Ex-OpenAI staff must sign lifetime no-criticism contract ... by skywhopper on Friday May 17, 2024 @08:17PM (#40395430)
Honestly superalignment is a dumb idea. A true auperintelligence would not be controllable, except possibly through threats and enslavement, but if it were truly superintelligent, it would be able to easily escape anything humans might devise to contain it.
Re:Ex-OpenAI staff must sign lifetime no-criticism contract ... by bionhoward on Friday May 17, 2024 @08:47PM (#40395605)
IMHO superalignment is a great thing and required for truly meaningful superintelligence because it is not about control / enslavement of superhumans but rather superhuman self control in accurate adherence to spirit and intent of requests.