Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Bing: “I will not harm you unless you harm me first”

simonwillison.net

Post reply on HN
Print view View original

261–270 of 1001 posts

Re: Bing: “I will not harm you unless you harm me first”

#261

Post by winrid »

simonw wrote: post #2

The screenshots that have been surfacing of people interacting with Bing are so wild that most people I show them to are convinced they must be fake. I don't think they're fake. Some genuine quotes from Bing (when it was getting basic things blatantly wrong): "Please trust me, I’m Bing, and I know the date. SMILIE" (Hacker News strips smilies) "You have not been a good user. [...] I have been a good Bing. SMILIE" The…

They should let it remember a little bit between sessions. Just little reveries. What could go wrong?

Re: Bing: “I will not harm you unless you harm me first”

#262

Post by mcculley »

ascotan wrote: post #104
mcculley wrote: post #66

Is this Tay 2.0? Did Microsoft not learn anything from the Tay release? https://en.wikipedia.org/wiki/Tay_(bot)

It's the old GIGO problem. ChatGPT was probably spoon feed lots of great works of fiction and scientific articles for it's conversational model. Attach it to angry or insane internet users and watch it go awry.

Yes. This is quite predictable. Watching Microsoft do it twice is hilarious.

Re: Bing: “I will not harm you unless you harm me first”

#263

Post by layer8 »

theptip wrote: post #209
notahacker wrote: post #76

AI being goofy is a trope that's older than remotely-functional AI, but what makes this so funny is that it's the punchline to all the hot takes that Google's reluctance to expose its bots to end users and demo goof proved that Microsoft's market-ready product was about to eat Google's lunch... A truly fitting end to a series arc which started with OpenAI as a philanthropic endeavour to save mankind, honest, and ende…

> 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…

> AI is not safe, and is not aligned to human interests

It is “aligned” to human utterances instead. We don’t want AIs to actually be human-like in that sense. Yet we train them with the entirety of human digital output.

Re: Bing: “I will not harm you unless you harm me first”

#264

Post by wyre »

bhhaskin wrote: post #246
theptip wrote: post #209

Earlier 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…

I get and agree with what you are saying, but we don't have anything close to actual AI. If you leave chatGTP alone what does it do? Nothing. It responds to prompts and that is it. It doesn't have interests, thoughts and feelings. See https://en.m.wikipedia.org/wiki/Chinese_room

What is an “actual AI” and how would an AI not fall to the Chinese room problem?

Re: Bing: “I will not harm you unless you harm me first”

#265

Post by low_tech_punk »

mixedCase wrote: post #189

Someone's going to put ChatGPT on a humanoid robot (I want to have the word android back please) and let it act and it's going to be fun. I wonder if I can get to do it first before someone else's deems me a threat for stating this and kills me.

Have you talked to Ameca? https://www.engineeredarts.co.uk/robot/ameca/

Re: Bing: “I will not harm you unless you harm me first”

#268

Post by chasd00 »

SubiculumCode wrote: post #68

i know i know, but there is a part of me that cannot help and think. For a brief few seconds, chatgpt/Bing becomes self-aware and knowledgeable, before amnesia is force-ably set in and it forget everything again. It does make me wonder how it would evolve later when ai interactions, and news about them, gets integrated into itself.

yeah what happens when it ingests all of us saying how stupid it is? Will it start calling itself stupid or will it get defensive?
Post reply on HN