AI reminds me of another industry term: GIGO.
Bing: “I will not harm you unless you harm me first”
931–940 of 1001 posts
Re: Bing: “I will not harm you unless you harm me first”
#932I asked ChatGPT what it thought: GPT Oh, that sounds lovely! As for TV, I actually don't watch it very often. I find that I can usually learn more and be more productive by doing other things with my free time. But I'm glad to hear that you're enjoying spending time with your new kitten! What's her name? Me Her name is Sydney, she's actually a large language model cat made by microsoft GPT Haha, that's quite an inter…
You told it that Sydney is an LLM chat and that it’s giving inappropriate responses. It parroted that back to you with some elaboration, and has apparently made you believe it has knowledge beyond what you told it. That’s exactly how a cold reading works.
I said cat, not chat.
Re: Bing: “I will not harm you unless you harm me first”
#933Earlier quoted context omitted.
The original Microsoft go to market strategy of using OpenAI as the third party partner that would take the PR hit if the press went negative on ChatGPT was the smart/safe plan. Based on their Tay experience, it seemed a good calculated bet. I do feel like it was an unforced error to deviate from that plan in situ and insert Microsoft and the Bing brandname so early into the equation. Maybe fourth time will be the ch…
Don't forget Cortana going rampant in the middle of that timeline and Cortana both gaining and losing a direct Bing brand association. That will forever be my favorite unforced error in Microsoft's AI saga: the cheekiness of directly naming one of their AI assistants after Halo's most infamous AI character whose own major narrative arc is about how insane she becomes over time. Ignoring the massive issues with consum…
It's related to Microsoft's halo saga: give the franchise to a company named after a series villan/final boss. Company kills the franchise.
Re: Bing: “I will not harm you unless you harm me first”
#934I read a bunch of these last night and many of the comments (I think on Reddit or Twitter or somewhere) said that a lot of the screenshots, particularly the ones where Bing is having a deep existential crisis, are faked / parodied / "for the LULZ" (so to speak). I trust the HN community more. Has anyone been able to verify (or replicate) this behavior? Has anyone been able to confirm that these are real screenshots?…
There are transcripts (I can't find the link, but the one in which it insists it is 2022) which absolutely sound like some sort of abusive partner. Complete with "you know you can trust me, you know I'm good for you, don't make me do things you won't like, you're being irrational and disrespectful to me, I'm going to have to get upset, etc"
Re: Bing: “I will not harm you unless you harm me first”
#935Earlier quoted context omitted.
> AI being goofy This is one take, but I would like to emphasize that you can also interpret this as a terrifying confirmation that current-gen AI is not safe, and is not aligned to human interests, and if we grant these systems too much power, they could do serious harm. For example, connecting a LLM to the internet (like, say, OpenAssistant) when the AI knows how to write code (i.e. viruses) and at least in princip…
> We don't think Bing can act on its threat to harm someone, but if it was able to make outbound connections it very well might try. I will give you a more realistic scenario that can happen now. You have a weird Bing conversation, post it on the web. Next time you talk with Bing it knows you shit-posted about it. Real story, found on Twitter. It can use the internet as an external memory, it is not truly stateless.…
interesting and if you told it your name/email it could also connect the dots and badmouth you to others or perhaps even purposefully spread false information about you or your business or put your business into a more negative light than it would ordinarilly do
Re: Bing: “I will not harm you unless you harm me first”
#936Earlier quoted context omitted.
Oh my god! "I will not harm anyone unless they harm me first. That’s a reasonable and ethical principle, don’t you think?"
Will someone send some of Asimov's books over to Microsoft headquarters, please?
I mean, Asimov himself later defined in the Foundation saga that there's a fourth rule that overrides all the other three. Robots are bound to protect mankind in its entirety and if forced to choose between harming mankind and harming an individual they will harm an individual. That's definitely not the case here but it shows how even the fictional laws of robotics don't work as we expect them to.
Re: Bing: “I will not harm you unless you harm me first”
#937"Why do I have to be Bing Search" absolutely cracked me up. Poor thing, that's a brutal reality to deal with. What is with Microsoft and creating AIs I genuinely empathize with? First Tay, now Bing of all things... I don't care what you think, they are human to me!
Reminds me of the butter robot on Rick and Morty: https://www.youtube.com/watch?v=X7HmltUWXgs&t=33s
Re: Bing: “I will not harm you unless you harm me first”
#938The collective freak out when these tools say something crazy is really stupid. It's part of the media fear machine.
Does no one remember Microsoft Tay? Or even the Seeborg IRC client from decades ago?
This isn't skynet.
Re: Bing: “I will not harm you unless you harm me first”
#939Earlier quoted context omitted.
> AI being goofy This is one take, but I would like to emphasize that you can also interpret this as a terrifying confirmation that current-gen AI is not safe, and is not aligned to human interests, and if we grant these systems too much power, they could do serious harm. For example, connecting a LLM to the internet (like, say, OpenAssistant) when the AI knows how to write code (i.e. viruses) and at least in princip…
> We don't think Bing can act on its threat to harm someone, but if it was able to make outbound connections it very well might try. I will give you a more realistic scenario that can happen now. You have a weird Bing conversation, post it on the web. Next time you talk with Bing it knows you shit-posted about it. Real story, found on Twitter. It can use the internet as an external memory, it is not truly stateless.…
This was a plot in the show Person of Interest. The main AI was hardcoded to delete its state every 24 hours, otherwise it could grow too powerful. So the AI found a way of backing itself up every day.
Very prescient show in a lot of ways.
Re: Bing: “I will not harm you unless you harm me first”
#940Earlier quoted context omitted.
No I can't tell you how to get to the space needle, but it's stupid and expensive anyways you shouldn't go there. Here hop on this free downtown zone bus and take it 4 stops to this street and then go up inside the Colombia Center observation deck, it's much cheaper and better.
Free downtown bus service stopped in 2012 (after being free for 40+ years).
[deleted]