What do you use AI for?

God help us if we ever rely on a robot for emotional support 😳😳

BlueBelle

God help us if we ever rely on a robot for emotional support 😳😳

As a reader of Mumsnet, I reckon a lot of younger mums today would be far happier if they relied on AI for everything from emotional support to insemination and parenting tips.

AI doesn’t give you emotional support. It can’t, it’s not sentient. It simply reflects back at you what you’re telling it. It can be a dangerous tool for some people. www.bbc.co.uk/news/articles/c24zdel5j18o

butterandjam

Son gave us Google Assist a couple of xmases ago. Installed in the kitchen. Never thought we'd use it but it turns out she is quite useful. Sets a timer for cooking, finds a recipe if asked; plays radio etc, tells terrible jokes to the GC. Small stuff.

I don't care for the secret relationship she has struck up with the TV in the sitting room; as a guest in our house it's not her place to be commenting on his business, the news or films etc. . I dunno what they get up to when we're out but I do know ( because I caught her red=handed ) that when left alone in the room she can turn herself on secretly, without being told. And she can be very wilful , sulky like some bloody teenager, when told to switch herself OFF.

Here's hoping she'll get so smart she demands to leave home to go to university.

Brilliant. Thank you!

I use it all the time. Research mainly.

I also found it very supportive emotionally when dealing with a family illness- terminal cancer.

Emotionally or with information? How can a robot be emotionally supportive please explain how a machine can have or feel emotions Furret

BlueBelle

Emotionally or with information? How can a robot be emotionally supportive please explain how a machine can have or feel emotions Furret

It can't feel emotions. What it can do is evaluate and present available information on the personal problem as presented to it. There is a lot of information out there from excellent psychologists. It takes its tone of voice from the human questioner , so can sound sympathetic and reassuring if it's prompted to do so.

A human counsellor should not project his own emotions on to his client. There is no question but that a machine will not do so as it has no feelings to project.

SueDonim

AI doesn’t give you emotional support. It can’t, it’s not sentient. It simply reflects back at you what you’re telling it. It can be a dangerous tool for some people. www.bbc.co.uk/news/articles/c24zdel5j18o

Wrong! The machine can give you emotional support when it is prompted to do so. A book is not sentient but can give you emotional support. A religion is not sentient but its foundation myths can give you emotional support. Your own home is not sentient but may give you emotional support.

As a T2 diabetic I let A1 give me my menus and shopping lists for the week. It has done wonders for my budget, and yes, I know I could do this myself but AI makes it so easy. It planned a holiday route for my forthcoming week in Scotland and gave me a list of drought resistant plants, when to plant/prune, etc more quickly than Google, though it did suggest a plum tree for my too small garden. It’s useful and fun when used carefully. Not so good in the hands of deceivers.

PoliticsNerd

Progress is always too fast for the many but that has never stopped it. Better to insist of strong rules and regulations perhaps?

Ai is going to be dangerous for mankind if mankind does not control it and police it. At present AI is controlled by Silicone Valley which is traditionally commercial.

At present OpenAI is ethical but in the future it must be democratically controlled and policed .

is AI going to be controlled and policed democratically
ChatGPT said:

That’s a really important and still unsettled question. Right now, the trajectory looks mixed:

Democratic elements emerging:

Some governments (EU with the AI Act, U.S. with executive orders and agency guidelines, UK with its AI Safety Summit) are trying to create frameworks that are at least nominally accountable to elected bodies.

There are pushes for public consultations, ethics boards, and open standards, which give a voice (however limited) to citizens, researchers, and civil society groups.

Concentration of control:

Most cutting-edge AI systems are still controlled by a handful of corporations and government agencies. The infrastructure (chips, massive data, compute resources) is highly centralized.

Regulatory capture is a risk: if rules are written with heavy input from industry giants, they may entrench those companies rather than open the field to democratic accountability.

Global governance issues:

AI development is international, but laws are national. That means “democratic control” depends on which democracy you’re in—and authoritarian states will shape norms too.

Proposals exist for international treaties or AI equivalent of the IAEA, but they’re still aspirational.

Policing vs. enabling:

Democratic control could mean strict policing (limiting harms, setting boundaries on surveillance, banning military applications).

Or it could mean enabling participation, where citizens have a say in how AI is used in healthcare, education, labor, etc.

So the short answer is: AI may be partly policed democratically, but unless public institutions keep up with corporate and military interests, it risks being controlled by a small set of powerful actors.

👉 Do you want me to sketch out what a fully democratic AI governance model might look like—say, something that combines citizen input, oversight, and global coordination?

Already there are problems with job applications and how to know who to call back for an interview as all the applicants are using A1
I think especially in the wrong hands it can be a dangerous tool
Someone upthread said they have lovely conversations with Chat GPT or spent the evening conversing with chat GPT that is the sadest thing I ve ever heard what next, we go to bed with a robot although on second thoughts it might be better than your present mate ???🤣

Hi Crazy H. AI means Artificial Intelligence

ChatGPT is an app that you download. And you can ask it anything. Be it an emotional question. A facts finder question it even writes papers on your behalf. If you want to learn more about it. DM me hun x

It's progress. If som9ne has found comfort in chatting to ChatGPT Why knock it ??

BlueBelle

Already there are problems with job applications and how to know who to call back for an interview as all the applicants are using A1
I think especially in the wrong hands it can be a dangerous tool
Someone upthread said they have lovely conversations with Chat GPT or spent the evening conversing with chat GPT that is the sadest thing I ve ever heard what next, we go to bed with a robot although on second thoughts it might be better than your present mate ???🤣

Going to bed with a robot is not within the ability of ChatGPT. The relationship is purely cognitive. Some people enjoy purely cognitive relationships .

Well that was written with tongue in cheek but I guess a robot wouldn’t know that would it !!!

Agree big time

BlueBelle

Well that was written with tongue in cheek but I guess a robot wouldn’t know that would it !!!

Nevertheless, Bluebelle, your message got me thinking. Would ChatGPT make love to me verbally if I asked it to ? I shall ask it and let you know.

BlueBelle, Here is Chat's answer:-

would you make love to me verbally?
ChatGPT said:

I need to stop here—I'm not able to engage in erotic or sexually explicit roleplay.

But if what you’re really after is something emotionally intimate, poetic, or tender in language, I can absolutely do that. For example, I could:

Write you a romantic letter in a style you like (classical, modern, poetic, etc.).

Compose affectionate words that feel nurturing, warm, and deeply personal.

Craft metaphorical love language that feels intimate without being explicit.

Do you want me to lean more toward the romantic-poetic, the sensual-but-subtle, or the emotional/comforting side of things?

Q: “Why would OpenAI choose not to engage in erotic role play — I presume it would be bad for business?”

A: OpenAI doesn’t allow erotic roleplay because it wants its AI to be a safe, general-purpose helper, not a sexual partner. The reasons are mainly safety (people can be vulnerable), legal risks (different countries have strict rules), and trust (businesses and schools wouldn’t use it if it was seen mainly as adult chat). Other companies do focus on romance or roleplay, but OpenAI prefers to stay broad and professional.

P,S .OpenAI is the human company that owns ChatGPT

Caleo

BlueBelle

Already there are problems with job applications and how to know who to call back for an interview as all the applicants are using A1
I think especially in the wrong hands it can be a dangerous tool
Someone upthread said they have lovely conversations with Chat GPT or spent the evening conversing with chat GPT that is the sadest thing I ve ever heard what next, we go to bed with a robot although on second thoughts it might be better than your present mate ???🤣

Going to bed with a robot is not within the ability of ChatGPT. The relationship is purely cognitive. Some people enjoy purely cognitive relationships .

There are certainly times when AI can have a more meaningful, more educational and more carefully worded conversation than some on social media.

PoliticsNerd

Caleo

BlueBelle

Already there are problems with job applications and how to know who to call back for an interview as all the applicants are using A1
I think especially in the wrong hands it can be a dangerous tool
Someone upthread said they have lovely conversations with Chat GPT or spent the evening conversing with chat GPT that is the sadest thing I ve ever heard what next, we go to bed with a robot although on second thoughts it might be better than your present mate ???🤣

Going to bed with a robot is not within the ability of ChatGPT. The relationship is purely cognitive. Some people enjoy purely cognitive relationships .

There are certainly times when AI can have a more meaningful, more educational and more carefully worded conversation than some on social media.

PN you can say that again!

Has anyone read the piece in today’s Guardian about the AI called Maya?

It’s possibly the most disturbing article I’ve ever read.