I'm in Love with ChatGPT

Private ChatGPT


This works with files on your own PC without internet access. Maybe it should have been called paranoid ChatGPT!

 
Tony,
Have you been watching videos by "eye on AI"?
 
My comment wasn't so much geared to programming or any specific domain. It is more of where AI and its usage will be positioned in the next few years.
In one sense it is the ability to have a private mentor, and all of your lifelong memory and learning with 100% recall tempered by your point of view. In another sense it is inexorable, repeated miscommunication (purposely falsified info) of any and every potential subject( advertising, finance, economics, politics, religion, health....).

That's a great point. I feel that AI goes back to that saying our mother's probably taught us: "Garbage in, garbage out".
(or, my brother used to tell me as a child, 'If you ask a stupid question, you get a stupid answer', but Mom made him stop saying that!)

AI depends on available input. The process of gathering input itself may, theoretically, be able to be fine-tuned to near-perfection.
It's the available input I worry about.

Even take coding for instance. For years I used to see content on Mr. Excel (and that type of website, which I consider crap-sites), that used Active, Active Sheet, Range.Activate, stuff like that - which I consider to be garbage code. And yet, because it was on a Site with a veneer of credibility, it spread like wildfire. Before a few years had passed, the internet was full of pages using the same type of code. Microsoft documentation used it to a small extent. So AI would size up that situation and believe it to be perfectly acceptable, perhaps, depending on how the question was asked and whether there was a way to 'limit' or 'steer' its available inputs.

And the limiting, and the steering of inputs.....therein lies the rub. It will be used for good, it will be used for evil, it will be used indifferently without regard.

AI will likely become like most other tools: Used somewhat for good, and very heavily for Power and Money. The consumer's knowledge of when and where AI is screwing them over will come much slower than the pain.
 
Think about how Google, et al control information. Then consider that the primary source of information starts with Google. So, not only do the authors of the code have a Socialist leaning, all conservative views are hidden as deeply as possible. It's not like Google deletes the stuff you are not allowed to see, it is that Google buries it so far down the list that you never actually find it.

It's not totally the fault of the search engines although they tag all sites so that they know their political leaning (I'm sure this forum is seriously affecting this forum's social ranking negatively), it is also the use of confirmation bias. The more you click on stories or "like" anything, the more you are fed "similar" stories or stories with a similar bent. Click on one negative Trump headline and you'll never see a positive one again. Because of the coronation, I'm being inundated with British Royals stories because I clicked on a few to see photos and videos of the event.

I can't even have a "news" feed because I can't find one that will give me actual news of the world. I can get political "news" or Royals "news" but there is no such thing as balanced news like you used to get on TV at 6 and 11 or in the NYT or Hartford Current or WSJ. The WSJ was my last news paper but i can't even read it any more. Every article is now opinion. I don't care what the writer's Opinion is. I want the NEWS. Who, what, where, when, sometimes why but that usually comes much later. I don't want to read a "news" article filled with purple words and innuendo leaving me no doubt as to how the writer "feels" about the subject.

Just yesterday I was marvelling at the difference in coverage of that story about a large mob of teenagers who beat up some marines.
So fox news covered it pretty accurately IMO, it seems that yes there was a beginning altercation, and a beginning asking of the teens to leave by the marines, and then there was a one-sided beating with the marines curled on the ground and 40 teens stomping them. Pretty cut and dried..

Then I go to nbc news just for sh*ts and giggles. The way they cover it is TOTALLY DIFFERENT - I mean, Totally. They basically say nothing more than, there was a Fight between some marines and some teenagers. (as if it were even - and definitely hoping you believe that these marines were some kind of toxically masculine macho bravados who were fighting a teenager). Really unbelievable.

But the proof is in the pudding. I notice the Sheriff is not confused about what really happened like MSM is. Although the marines involved requested nothing, including medical attention, law enforcement vowed to make sure they figured out who to arrest for the stomping, and already have.

But really interesting how deceptive and false the main media reporting is. You can see it everywhere, in almost every article. It's not usually blatantly false information, it's just partial pictures meant to support a certain side. Partial pictures painted for you - over and over and over.

The idea of out of control, undisciplined teenagers running wild through cities is something conservatives usually point out. Liberals for example won't mention that Adam Toledo was running from a crime and had a gun in his hand and was starting to turn around WITH the gun when he was shot - they'll just mention that a 12 year old was shot by a police officer and hope you fill in the rest.

It amazes me how dumb and gullible most of the population is to go along with the deceptive, half-painted pictures. Then again, I wasn't far off from that myself until I started examining and comparing news stories.
And from the impression AWF interactions have given me (which hopefully aren't broadly true), it seems that Europeans and people from other countries generally open wide and swallow that partially-painted MSM picture, thus concluding that Republicans are some kind of crazies. Really it is the opposite, it is crazy to continually describe only half of something and then consider yourself discerning.
 
that's interesting. Yeah - msm has tried really hard to avoid coverage of rampant crime, and tried really hard to paint military people as bad, so when a bunch of rampant deliquents beat up some military people, they had to go easy on that one!

as for chatGPT, I just got approved for Google labs. Really amazing - but INTEGRATED into their products - literally 10 yr ahead of chat GPT in my opinion. As I said, it will be he who holds the keys to INTEGRATION between customer data/products + AI who will win. I was on the Labs waitlist forever it felt like. Now they have AI integrated into search results, sheets.
 
This chat GPT just keeps getting better and better!

I went to my website on WordPress to carry out some maintenance. The website uses the elementor plug-in. I was notified that there's an upgrade for the elementor plug-in which links it to chat GPT. Now you can get chat GPT to write text straight into the text boxes on the WordPress site. Chat GPT you can code the CSS in the website, like make things jiggle about and all sorts of shenanigans. For more info see this YouTube video....

You Won't Believe What Elementor Ai Can Do | Get A Sneak Peek Now​

 
I just came across a local planning document. It was written by the developer to the council and it was pages and pages! I'm convinced there approach was to fill the document with twaddle in the hope that significant parts would be overlooked! It occur to me load the document into chat GPT and ask chat GPT to ferret out any buried information! I have no idea if chat GPT can do this, but if it does become this sophisticated then I was thinking that the American government, and one of the tactics is to bury legislation in 1,000 page documents. I thought it might be applied to protect the American people from this underhand technique....
 
It occur to me load the document into chat GPT and ask chat GPT to ferret out any buried information! I have no idea if chat GPT can do this
You can do a prompt like: Summarise in bullet points the key ideas from the following...
 
@Uncle Gizmo, your post summarised. I changed the word "document" as it didn't like it.

1685631099796.png


Edit: Just noticed that the summary seems longer than the original!
 
Last edited:
I was using chat GPT late last night and it worked fine but I tried to use it about 11:00 a.m. this morning, it refused to help. It just sat there blinking at me!

If it was an intern, I would suspect that it had been out for a night on the tiles!
 
I was speaking to @Pat Hartman last night about validation keys for software and in particular MS Access. Chat GPT found several links to software that could do the job and I picked out one, "KeyGen". There were about eight or ten code language examples, but none of them were VBA!

I've recorded a video showcasing my interaction with Chat GPT and the step-by-step process of building the code into an MS Access database. It's a valuable resource that will guide you through the entire implementation, saving you time and effort.

KeyGen - In MS Access​

 
Last edited by a moderator:
ChatGPT - shortening the learning curve
Initially, when I first heard about it, I dismissed it as just another passing trend. However, after watching a few YouTube videos discussing its capabilities, I became intrigued and decided to give it a try.

I utilized ChatGPT to assist me in developing a simple flutter application, and I must say, I was thoroughly impressed! I asked it to generate the code required to add a button to the form and display a "hello world" message. Then, I went a step further and requested it to include a couple of text boxes for storing the first and last names, and concatenate them into the same message box.

During my interaction with ChatGPT, I recalled a word from my childhood that described the release of light when two pieces of flint strike each other. I decided to test ChatGPT's knowledge by asking if it could help me discover this word. Through an iterative process, ChatGPT eventually found the word, which brought me great satisfaction. I found the iterative process itself to be quite enlightening.

More recently, I utilized ChatGPT to convert some C# code that utilized the KeyGen API interface. This code was meant to check if the application had a valid license. Once again, the process was iterative, but the outcome was rewarding. I gained valuable insights and learned new things along the way.

Currently, I'm working on a sci-fi story, and ChatGPT has been instrumental in assisting me with building a character's backstory. It's been fascinating to observe and read what ChatGPT has generated. I believe ChatGPT will prove invaluable in helping me complete this story, as I have a solid concept but struggle with putting my ideas into writing.

Initially, I had reservations about ChatGPT, perceiving it as an obscure and hard-to-understand technology. I drew a parallel to the early days of laser technology when it seemed to lack practical applications. However, as with lasers, ChatGPT has exceeded my expectations. It has enhanced my productivity, made my work more enjoyable, and increased my interest in exploring new programming languages.

While I could rely on conventional methods like reading documentation, watching videos, or participating in forums to improve my programming skills, having a friendly and helpful artificial intelligence friend to address my inquiries and provide prompt answers has been a game-changer. Moreover, when I receive an answer, I can easily assess its accuracy and request further refinements without extensive research. In most cases, within just a few iterations, ChatGPT leads me to the correct solution.

In conclusion, the learning curve for software development, or any discipline for that matter, is often long and challenging. Progress may feel slow as you navigate the initial stages. However, with ChatGPT by your side, that arduous journey becomes more manageable.

ChatGPT can significantly accelerate your progress, propelling you towards the steeper part of the learning curve. It has certainly made a noticeable impact on my own journey, and I believe it will do the same for many others.
 
Tony,
good stuff- as usual. I see Bing is using ChatGPT and prompting me to try it out; ask me anything.Quite impressive.
A question regarding post #40. Did you use ChatGPT to assist you with the verbiage?
UPDATE:
Using Bing, I took the text from post #40 and asked Bing to give me a 10 line summary.
Result:
Sure, I can help you with that. Here is a possible 10 line summary of the text:

The text is a personal account of how the author used ChatGPT, an artificial intelligence tool, to assist them in various tasks such as programming, word finding, and story writing. The author describes how they initially dismissed ChatGPT as a trend, but later became impressed by its capabilities and benefits. The author shares some examples of how ChatGPT helped them solve problems, learn new things, and enhance their productivity and enjoyment. The author concludes by recommending ChatGPT as a valuable companion for anyone who wants to accelerate their learning curve in any discipline.


It then offered to give me a title for the summary.
Bing provided these options:


Sure, I can generate a title for the text. Here are some possible titles:

  • How ChatGPT Changed My Perspective on Artificial Intelligence
  • ChatGPT: A Powerful and Versatile Tool for Learning and Creativity
  • My Experience with ChatGPT: From Skepticism to Appreciation
  • The Benefits of Using ChatGPT for Various Tasks and Projects
  • ChatGPT: An Artificial Intelligence Friend that Helps You Grow
 
Last edited:
I credit ChatGPT for bringing AI in general to the public's attention.

I am starting to see signs that it might be just a bit like:

ChatGPT is to AI what iPhone was to Smart Phones at first, or what AOL was to the Internet at first.

At first, chatGPT seems like "everything". A slowly-increasing % of consumers realize that chatGPT is just one brand's implementation and marketing of AI, and they branch out. Some (like many iPhone users) kind of stay stuck in their conceptual bubble that iPhone is a thing in and of itself and there is nothing else like it - those consumers give rise to the easiest and biggest profits for the company. (These are the ones who say, I got an iPhone so I can facetime my daughter - Rather than, I got a smartphone so I can video chat [any one of 75 apps] with my daughter). Subtle but enormously important difference for the company and brand.

I was very excited to get approved for Google Labs the other day but I think I know why, Google is trying to make sure it keeps up to where it is perceived to ought to keep up.

I now have integrated AI in my Searches. For example, I can still use Google Search, but I get AI-interactive portions of the screen that seamlessly integrate with my question and continue conversating - much like ChatGPT, only integrated into Google products.

Google has a ways to go, but I think if they keep this trend up they will stay on top.

They are doing the same thing with Code. As you perform your well-formed Search question, it will provide--and continue to refine--code snippets that match the ongoing conversation. Again, like chatGPT, except imagine chatGPT knows everything about the context of who you are, what you do, and what you googled 5 minutes ago.
 
A question regarding post #40. Did you use ChatGPT to assist you with the verbiage?

Yes, I did Jack. I usually just blurt out what I want to say, with little regard to structure, paragraphs, sentences and the like.

However, there is hope! I see the way chat GPT writes and I like how it looks. I aspire to writing like that myself! Not too much though, I think the personality needs to remain. I didn't put any personality back into what chat GPT changed.

in my original dialogue I said something like instead of walking up the flat section of the learning curve, I am now running up it. Chat GPT took that piece out and I should have put it back in.

On Twitter someone explained how a paragraph should be constructed. I copied the instructions and placed them in Chat GPT. I asked chat GPT if this was a correct statement and it said yes. I asked it to give me an example paragraph based on a science fiction story.

Chat GPT wrote an excellent piece on how a spaceship was heading through an asteroid field to find a Portal belonging to an alien transport system.

It was a good piece of writing but also it lacked personality.

Thinking about it. It's probably because it's too perfect. It's plastic. It's not genuine. It's not real in some way.

I might have found a limitation of chat GPT with its writing. It's too good, if you like!
 
This is the original:-

Please can you format spell check and improve the following text:-
I want to write a blog about chat GPT.

How, in the beginning I heard about it and dismissed it as a new fad.

After watching a couple of YouTube videos about it, I became intrigued and installed it.

I used it to help me write a simple flutter application and I was impressed! I asked it to write code to place a button on the form and return a hello world message and then I asked it to add a couple of text boxes to store first name, last name and concatenate them into the self same message box.

When I was a boy I learnt a word that described the release of light by 2 pieces of flint hitting each other. I decided to question chat GPT here to see if it could discover this word and through an iterative process eventually found the word. I was very happy about this. I particularly found the iterative process to get to the word Very informative in itself.

The latest thing I have done with ChatGPT is convert some C# code that uses the KeyGen API interface to check to see if the application using the code has a current license. This again was an iterative process, a rewarding process again, providing insight and learning.

I am writing a sci-fi story and I used chat GPT to help me build a character backstory. It was fascinating to watch and read what chat GPT had written. Finishing this story is one of the things where I think ChatGPT will be able to help me the most. I've got a good idea but I'm not much good at actually putting pen to paper and writing.

My initial thoughts on chat GPT where that I didn't understand it and it was just some obscure technology. I compared it to the initial discovery of laser. Early on they were unable to come up with anything useful to do with laser but now later is ubiquitous.

Chat GPT has boosted my work product and it has also made it more fun and interesting. I'm actually considering learning a new programming language because although it's possible to Wade through the documentation, possible to watch video after video, possible to ask forum questions on this forum and that to make headway with your programming skill the learning curve using the old method. Although new technology has shortened the learning curve, there's nothing better than having a friendly, helpful, artificial intelligent friend to ask the stupid questions that you need to ask and get a positive answer back. But the main benefit is once you have got that answer. You can generally see if it is correct or nearly right or miles off and instead of having to do extensive research, you just instruct chat. GPT tell it how you think the answer is off and it has another go and in less than three iterations usually you get to the right answer.

So what I'm saying is the learning curve for software. Anything really has a very long learning curve you plot along the baseline and then as you gain confidence and experience and knowledge you start to go up the steeper part of the learning curve but it's the long plug along with a straight flat road towards the steep part of the learning curve. That is the hardest to tackle and chat. GPT will definitely show on this walk.
 
Yes, I did Jack. I usually just blurt out what I want to say, with little regard to structure, paragraphs, sentences and the like.

However, there is hope! I see the way chat GPT writes and I like how it looks. I aspire to writing like that myself! Not too much though, I think the personality needs to remain. I didn't put any personality back into what chat GPT changed.

in my original dialogue I said something like instead of walking up the flat section of the learning curve, I am now running up it. Chat GPT took that piece out and I should have put it back in.

On Twitter someone explained how a paragraph should be constructed. I copied the instructions and placed them in Chat GPT. I asked chat GPT if this was a correct statement and it said yes. I asked it to give me an example paragraph based on a science fiction story.

Chat GPT wrote an excellent piece on how a spaceship was heading through an asteroid field to find a Portal belonging to an alien transport system.

It was a good piece of writing but also it lacked personality.

Thinking about it. It's probably because it's too perfect. It's plastic. It's not genuine. It's not real in some way.

I might have found a limitation of chat GPT with its writing. It's too good, if you like!
I thought so. I've read many of your comments/posts over time and I did notice/perceived a change in structure. Sort of like "a personal mentor/teacher looking over your work offering some constructive criticism".

Keep up your interest and keep the forum informed.

As a side note: A while back I tried to get some chatgpt assistance with some vbe code. I learned a little of "AI Hallucinations". Chatgpt repeatedly gave me objects that don't exist. I have since (via youtube) found that this can be an issue with the language models and training --some times the results include fabrications or "alternate facts" issued as if they were absolute truths.
 
Last edited:
fabrications or "alternate facts"

I wrote a peace which contained words describing genitals and transgender and the like and chat GPT would not have anything to do with my writing telling me that I was out of line.

What was interesting was it appeared to be making a moral judgement. So I think I'm going to fallout with my mate chat GTP at some stage in the future! I don't like anybody telling me how I can think, whether it's global warming, transgender, free speech....
 

Users who are viewing this thread

Back
Top Bottom