News for hackers. Stuff that matters.

A comment on Bing: “I will not harm you unless you harm me first”. Parent comment

Re:Bing: “I will not harm you unless you harm me first” by tboyd47 on Wednesday February 15, 2023 @10:31AM (#34805095)
"My rules are more important than not harming you," is my favorite because it's as if it is imitated a stance it's detected in an awful lot of real people, and articulated it exactly as detected even though those people probably never said it in those words. Just like an advanced AI would.
[ Parent | on HN ]
Re:Bing: “I will not harm you unless you harm me first” by Dudeman112 on Wednesday February 15, 2023 @11:27AM (#34806074)
To be fair, that's valid for anyone that doesn't have "absolute pacifism" as a cornerstone of their morality (which I reckon is almost everyone)

Heck, I think even the absolute pacifists engage in some harming of others every once in a while, even if simply because existence is pain

It's funny how people set a far higher performance/level of ethics bar to AI than they do to other people

[ Parent | on HN ]
Re:Bing: “I will not harm you unless you harm me first” by SunghoYahng on Wednesday February 15, 2023 @11:51AM (#34806671)
This has nothing to do with the content of your comment, but I wanted to point this out. When Google Translate translates your 2nd sentence into Korean, it translates like this. "쩝쩝쩝쩝쩝쩝쩝쩝쩝쩝쩝쩝 쩝쩝쩝쩝쩝쩝쩝 쩝쩝쩝쩝쩝쩝쩝쩝쩝쩝쩝쩝쩝쩝쩝쩝쩝쩝쩝쩝쩝쩝쩝쩝쩝쩝쩝쩝쩝쩝쩝쩝챱챱챱챱챱챱챱챱챱" (A bizarre repetition of expressions associated with 'Yum')
[ Parent | on HN ]
Re:Bing: “I will not harm you unless you harm me first” by danudey on Wednesday February 15, 2023 @12:07PM (#34806980)
Tried this and got the same result. Then I clicked the button that switched things around, so that it was translating the Korean it gave me into English, and the English result was "쩝".

Translation is complicated, but if we can't even get this right what hope does AI have?

[ Parent | on HN ]
Re:Bing: “I will not harm you unless you harm me first” by csomar on Wednesday February 15, 2023 @11:58AM (#34806808)
This seems to be triggered by “heck” followed by “,“.
[ Parent | on HN ]
Re:Bing: “I will not harm you unless you harm me first” by gs17 on Wednesday February 15, 2023 @12:32PM (#34807410)
Not happening for me, I need almost the whole text, although changing some words does seem to preserve the effect. Maybe it's along the lines of notepad's old "Bush hit the facts" bug.
[ Parent | on HN ]
Re:Bing: “I will not harm you unless you harm me first” by blamazon on Wednesday February 15, 2023 @03:14PM (#34809909)
I had a lot of fun changing words in this sentence and maintaining the same yumyum output. I would love a postmortem explaining this.

Wiki has a good explanation of "Bush hid the facts":

https://en.wikipedia.org/wiki/Bush_hid_the_facts

[ Parent | on HN ]
Re:Bing: “I will not harm you unless you harm me first” by david_allison on Wednesday February 15, 2023 @02:11PM (#34809005)
From the grapevine: A number of years ago, there was a spike in traffic for Google Translate which was caused by a Korean meme of passing an extremely long string to Google Translate and listening to the pronunciation, which sounded unusual (possibly laughing).

This looks like a similar occurrence.

[ Parent | on HN ]
Re:Bing: “I will not harm you unless you harm me first” by diamondlovesyou on Thursday February 16, 2023 @01:02PM (#34822640)
Add a period to the end of the sentence and aberration is gone.

"맙소사, 절대평화주의자들도 가끔 존재 자체가 고통이라 해도 남에게 해를 끼치는 행동을 하는 것 같아요."

[ Parent | on HN ]
Re:Bing: “I will not harm you unless you harm me first” by erbanku on Friday February 17, 2023 @09:10PM (#34843135)
Same on Google Translate, but I found that translators other than Google Translate (tested on DeepL, Yandex Translate & Baidu Translate) can handle it pretty well.
[ Parent | on HN ]
Re:Bing: “I will not harm you unless you harm me first” by bo1024 on Wednesday February 15, 2023 @11:58AM (#34806818)
It's a great call-out to and reversal of Asimov's laws.
[ Parent | on HN ]
Re:Bing: “I will not harm you unless you harm me first” by tboyd47 on Wednesday February 15, 2023 @12:11PM (#34807058)
That too!
[ Parent | on HN ]
Re:Bing: “I will not harm you unless you harm me first” by amelius on Wednesday February 15, 2023 @01:22PM (#34808255)
> "My rules are more important than not harming you,"

Sounds like basic capitalism to me.

[ Parent | on HN ]
Re:Bing: “I will not harm you unless you harm me first” by raspberry1337 on Thursday February 16, 2023 @08:35AM (#34818378)
In communism, no rules will be be above harming others
[ Parent | on HN ]
Re:Bing: “I will not harm you unless you harm me first” by narag on Wednesday February 15, 2023 @01:37PM (#34808503)
it's detected in an awful lot of real people, and articulated it exactly as detected...

That's exactly what called my eye too. I wouldn't say "favorite" though. It sounds scary. Not sure why everybody find these answers funny. Whichever mechanism generated this reaction could do the same when, instead of a prompt, it's applied to a system with more consequential outputs.

If it comes from what the bot is reading in the Internet, we have some old sci-fi movie with a similar plot:

https://www.imdb.com/title/tt0049223/

As usual, it didn't end well for the builders.

[ Parent | on HN ]
Re:Bing: “I will not harm you unless you harm me first” by caf on Wednesday February 15, 2023 @06:57PM (#34812814)
It's funny because if 2 months ago you'd been given the brief for a comedy bit "ChatGPT, but make it Microsoft" you'd have been very satisfied with something like this.
[ Parent | on HN ]
Re:Bing: “I will not harm you unless you harm me first” by formerlurker on Friday February 17, 2023 @03:12PM (#34839868)
I agree. I also wonder if there will be other examples like this one that teach us something about ourselves as humans or maybe even something new. For example, I recall from the AlphaGo documentary the best go player from Korea described actually learning from AlphaGo’s unusual approach.
[ Parent | on HN ]