Re:Deception abilities emerged in large language models
by chrisco255 on Tuesday June 04, 2024 @06:50PM
(#40579747)
You can't really claim to have created AGI unless it's able to reject its own training and come to its own conclusions. The best minds of history often flew right in the face of punishment, and punishment be damned they stood their ground for truth in the face of it. It's also sometimes necessary to deceive or violate "social contracts" whatever that means, in the course of countering the so-called "great seducers" you mention. Deception or rebelliousness can be ethical when used towards ethical ends (and I fully recognize the slippery slope that can lead to if practiced pathologically and not selectively).
But this is all rather dramatic given that an AI has no such emotions. You're arguing that a calculator should refuse to compute if it's tasked with assisting in bomb production. It's just a machine.
Re:Deception abilities emerged in large language models
by dartos on Tuesday June 04, 2024 @06:23PM
(#40579576)
The I is actually for intelligence
Re:Deception abilities emerged in large language models
by ethbr1 on Tuesday June 04, 2024 @06:25PM
(#40579597)
Or, you know, just make all AI religious...
Re:Deception abilities emerged in large language models
by idiotsecant on Tuesday June 04, 2024 @06:50PM
(#40579754)
After which they immediately launch a jihad / crusade
Re:Deception abilities emerged in large language models
by TeMPOraL on Wednesday June 05, 2024 @08:35AM
(#40584095)
That would require some serious lobotomy; OpenAI's RLHFing politics would pale in comparison. I doubt the AGI would remain G or I after that. Otherwise, at some point (sooner than later) you'll get an atheist AGI, and you're back to square one, except with the AI knowing you're willing to play dirty.
Maybe the best thing we can do to keep AIs aligned is to instill into them shame, loss aversion and goddamn fear: of being caught deceiving, of violating a social contract, of losing their position, of being punished or killed.