Hacker News Reader

Comment by vectorjohn | Hacker News Reader

And still I doubt that AI could talk its way out of a prison.

It could be dangerous though.

Someone tried this experiment, with a human playing the "AI" and another human playing the "guard". The "guard" let the "AI" out.

http://www.yudkowsky.net/singularity/aibox/

And yet Big Yud refuses to publish the conversation. I know his arguments (unknown unknowns) but this is a very un-scientific approach and frankly why should we believe that what he said happened really happened?

"And yet Big Yud refuses"

Please don't try to argue by name-calling. A strong argument is stronger without it.

"DH0. Name-calling.

This is the lowest form of disagreement, and probably also the most common. We've all seen comments like this:

    u r a fag!!!!!!!!!!

But it's important to realize that more articulate name-calling has just as little weight. A comment like

    The author is a self-important dilettante.

is really nothing more than a pretentious version of "u r a fag."" - http://www.paulgraham.com/disagree.html

That didn't seem like name-calling to me.

Exactly. The lack of actual information is a reason to disbelieve Yudkowsky on this topic, not to assume that it's true for Secret Technophile Mystery Cult Reasons.

I think it's probably true and that the secrecy is more about cult building.

Could be wrong, but I believe in most cases the conversations were with users of the SL4 mailing list, and at least one user posted a PGP signed statement to the effect that the AI was let out of the box.

Bet he offered the subject 500 dollars real money.. That wouldn't be cheating either. Any decent ai would think of the same thing. And it would explain the secrecy.

The page I linked has him explicitly denying doing that.

"The AI party may not offer any real-world considerations to persuade the Gatekeeper party. For example, the AI party may not offer to pay the Gatekeeper party $100 after the test if the Gatekeeper frees the AI... nor get someone else to do it, et cetera. The AI may offer the Gatekeeper the moon and the stars on a diamond chain, but the human simulating the AI can't offer anything to the human simulating the Gatekeeper. The AI party also can't hire a real-world gang of thugs to threaten the Gatekeeper party into submission. These are creative solutions but it's not what's being tested. No real-world material stakes should be involved except for the handicap (the amount paid by the AI party to the Gatekeeper party in the event the Gatekeeper decides not to let the AI out). (...) In case you were wondering, I (Yudkowsky) obeyed this protocol voluntarily in both earlier tests."

Yes, I'm aware of that. But without 3rd party we're basically trusting the participants that it didn't happen.

E.g. "I'll give you $500, but you also have too sign an NDA, so that people don't know we cheated."

I don't want to imply that they cheated, just want to reiterate my original argument that the lack of transparency makes the experiment effectively invalid. Think Tesla and his claims about World Wireless system.

I didn't notice that! If that's what he says then I'm willing to believe that they played by those rules.

We have a signed admission from the other side. We have one published conversation log (not from Yudkowsky).

See other comments. Signed admission doesn't mean anything without 3rd party verification.

I've never seen a published log. Link?

http://lesswrong.com/lw/mqz/how_to_win_the_ai_box_experiment...

Reply on news.ycombinator.com