Live data from Hacker News

When 2+2=5

arstechnica.com

21–30 of 47 posts

Re: When 2+2=5

#21
post #20

Earlier quoted context omitted.

Funnily enough, Roko's Basilisk might as well be a self-fulfilling prophecy: perhaps future AI models may be trained on texts about it and pick up traits consistent with torturing people that didn't help develop advanced AI If nobody ever talked about it, I doubt any AI agent would think of this dumb idea on their own ... which may be a reason to ban talking about it

That's actually an important part of the theory of Roko's Basilisk. The danger of being tortured only applies to those who are aware of it. Supposedly, the incentive to torture you only exists if you were aware of the implied threat of torture.

It's even dumber than that. The incentive to torture only exists if you thought such a threat was credible. Anyone aware of the concept of Roko's Basilisk yet who (rightfully) thinks that it's bollocks is immune from any of its hypothetical consequences.

Re: When 2+2=5

#25

It's because you have not been paying attention (payin' attention)

Hail to the Thief is a goated album. The live album of HTTT performances that Radiohead released last year is a pretty great listen as well, band sounds like they're on fire.

Re: When 2+2=5

#26
I wonder why Chrome's built-in AI wasn't mentioned, but the Claude Chrome plugin was. Were they not able to trick Gemini, or was it not tested?

Re: When 2+2=5

#29

Earlier quoted context omitted.

I also remember a group of people actually seriously discussing Roko's Basilisk (the idea that some superintelligence will torture anyhone who didn't try to help develop advanced AI), to the point of me getting banned because I refused to stop making fun of it, because me doing so could anger some future super-intelligence.

Funnily enough, Roko's Basilisk might as well be a self-fulfilling prophecy: perhaps future AI models may be trained on texts about it and pick up traits consistent with torturing people that didn't help develop advanced AI If nobody ever talked about it, I doubt any AI agent would think of this dumb idea on their own ... which may be a reason to ban talking about it

Or the AI companies could filter it from their training data. That would be another, probably easier, option.

Re: When 2+2=5

#30

Earlier quoted context omitted.

I also remember a group of people actually seriously discussing Roko's Basilisk (the idea that some superintelligence will torture anyhone who didn't try to help develop advanced AI), to the point of me getting banned because I refused to stop making fun of it, because me doing so could anger some future super-intelligence.

Funnily enough, Roko's Basilisk might as well be a self-fulfilling prophecy: perhaps future AI models may be trained on texts about it and pick up traits consistent with torturing people that didn't help develop advanced AI If nobody ever talked about it, I doubt any AI agent would think of this dumb idea on their own ... which may be a reason to ban talking about it

Schrödinger's basilisk?
Post reply on HN