What are your thoughts on AI?
I'm quite experienced in using this particular chatbot model
What the hell do you use it for.......IRL?......based on your own assessment of its capabilities? Genuine question - I am interested!
Your phrasing needs to be
Respectfully, my phrasing doesn't "need to be" anything - although I do appreciate that you were trying to help.
I'm quite experienced in using this particular chatbot model, and I know that asking such a question in this way is pretty futile.
I posted the exchange to demonstrate how, when it’s asked questions using colloquial English, it can regularly fail to answer them correctly.
Not only that, but it will also keep on making similar errors when asked to try again, even when the user has stressed that all of the criteria must be met (the same criteria that it keeps relaying back to that user each time, as if confirming that it's understood them).
The example I've used is one that enables us to see, pretty easily, that what it said is wrong. Bigger issues can obviously arise if errors are less clear to us.
In my view, we shouldn't need to phrase our questions in very specific and rigid ways (similarly to how, say, computer programmers / coders might structure queries). That, to me, would defeat the object of the exercise.
Of course, there are different and much more advanced models than this, which will return better results. Capabilities will obviously also improve over time, including in the "free to use" versions.
In the meantime, though, I feel it's always worth treating replies from chatbots with a high level of caution.
On that note I find it interesting, what Samsung are doing with their flagship phones. Offering them with oodles of convenient AI. Giving their consumers two years to get really used to it all - then, end of 2025, withdrawing the teat.
You can still have it, only now if you want it that bad, you will have to pay a monthly subscription for it. At least for the best bits.
Clever aren't they.
Olivia Coleman is a stage name......her actual name is Sarah Sinclair.
Your phrasing needs to be more explicit - I tweaked it to be:
list 5 british actors with a surname starting with the letter s and aged between 40 to 49
and it gave an improved (but still imperfect) list:
I suspect that it needs to be refined further as it is not really picking up the surname value. I tweaked "starting with" to be "beginning" and it improved again.
It does show that it is a mix of us assuming the way we phrase it will match its understanding. It is improving however at an exponentional rate.
Me: List five British actors aged in their 40s whose surnames start with S.
ChatGPT: Here are five British actors in their 40s whose surnames start with "S":
I hope not either, I've had loads of arguments with techies and nerds about my treatment of computers, that I shouldn't shout at them or threaten them, these people take it so seriously. Oddly enough they never want to help me with my tech problems, just tell me off and/or laugh at me as I have yet another disaster.
I often have problems getting a word in during conversations with more than one person and end up saying nothing, I could just see me being talked over by an "assistant" and shut down, I suppose the only advantage would be that I could unplug it, although with all thw battery life in these things probably even that wouldn't work. And what about these fridges that order your shopping for you? What if it ignores you and you end up with 200 pints of milk you don't want, I know its supposed to be easy to use these things, but we all know they never are in reality.
The medical and scientific potential is massive, but the reality of it isn't that we need to fear AI, it's the people who own it.
History has proven that people with money, use new technology to make themselves more money. Greed will be the driver behind the evolution of AI and will decide it's direction based on where it can benefit those who own it.
I wonder if all these smart gadgets work when thrown out of a window and runover by a car?
Don't worry, a day will come soon when the bleeding heart liberals with give AI rights and you will be fined for deliberately abusing them.
I hope not.
AI like so many other things, seem to be there to stop you having time to do the things you enjoy, whilst giving you more time to do the things you don't.
I wonder if all these smart gadgets work when thrown out of a window and runover by a car?
I agree that it is not good in some cases, for example where it replaces human employees. I also don't like these things that you talk to in the home and they do things for you. I have been in people's houses where they have had to tell it not to do something because it picks up on conversation.
Daisy sounds like a good use of AI, but one of the few. I think some of the medical advances could be good like checking mamograms and stuff, but to my mind it still needs to proved over a longer term. Over all I'm not in favour of it or more computerisation of life.
I have just read about Daisy the AI who is used by a phone network to speak to scammers. I have listened to a clip of her who sounds like a lovely old lady who enjoys baking and winds up the scammer in her conversations where she sounds confused. I don't know quite how it works but sounds a good idea.
Recently completed some training on how to make use of copilot (Microsoft AI assistant) and it went into other gen AI principles.
The thing I will never forget are the words "AI will produce inaccurate content with an extremely high level of confidence "
They're very powerful and given enormous sets of data AI and ML can find patterns and solutions in minutes that would take humans years, if they even could. But it's only as good as it's data and it's Training, it can introduce extreme bias (naturally from statistics) and even hallucinate.
The bottom line is"check it's work "
Technology isn't in itself harmful, I mean we had stone tools at one time and thats quite a technological process. But progress on the other hand is a trickier thing, we might progress from learning a simple sum, 2+2=4, to something much more advanced, but when we talk about the progression of humans from an imagined state of ignorance to a rational science led state of progress, then we need to stop and unpack what that actually means. The idea of progress as a concept started with the so called Enlightenment, although it was only really enlightened if you were a wealthy white man. I think this ongoing ideology of progress is the cause for a lot of the worlds problems today.
Or.....creative individuals already RARELY find success.....and have always RARELY succeeded?
That is a possibility too? I mean, who would know?!
This can occur through either laziness, or AI, or simply not having the time.
Or burnout!!
I just wonder if we may eventually evolve so that creative individuals do not succeed. Or maybe I am catastrophising !! Or maybe it is only seen as a catastrophe in the time and space we exist now.
I am in agreement with everything you say. Art and its proceses are fundamental to life. I was in a shop after I had posted and wondered about all the mass produced cushions and light fittings. Technology has mostly made these so I was wondering what the difference may be to my ideas above. I'm not sure they are that far removed really. The world possibly may split as you suggest as a possibility, but the direction of humanity always seems to be "progress" and in the long run I wonder if creativity might eventually evolve out of us. I think we will have become hybrid human robots before this happens anyway. Crikey!!!
