I'm in Love with ChatGPT (1 Viewer)

[Uncle Gizmo]

Binoculars which incorporate AI for recognizing birds!

World's first-ever smart binoculars can identify 9,000 birds thanks to built-in AI

Swarovski AX Visio binoculars bring AI tech to the forefront of wildlife observation

www.digitalcameraworld.com

 

[Uncle Gizmo]

Have you tried the new version of Baird?

I haven't! Me and Bard didn't get on that well.

But! >>>>>>

Reading this article:-

Mastering Creative Writing with ChatGPT and Google Bard

This guide is designed to show you how to use AI tools like ChatGPT and Google Bard for creative writing. For centuries, writers have wrestled with the

www.geeky-gadgets.com

Which suggests using a combination of Bard and Chat GPT allows you to draw on both of the AI's expertise and come up with some excellent help with your story writing.

I can vouch for the capability of Chat GPT however I acknowledge that it doesn't have depth. I have yet to try bard, I will see if it gives me the required depth.

Interestingly the author of the afore mentioned blog post suggests you cite the ai's contributions...

I usually mention stuff that I've used AI to generate, (I have forgotten once or twice), and really, except for the necessity of the reader to know who is writing, is it necessary to mention the input from AI large language models? I don't see why. Accept for the benefit of the reader there's no benefit to the AI itself... .

I haven't used one yet but I understand there are websites which can help you produce a particular voice, like write for you in an Irish accent or a cockney accent. I've never seen any one cite and article, or even an online or book source for such information. Really, it would look a bit silly if you said oh "that last dialogue was got from the meridian encyclopedia of cockney accents!" It would be like saying I used this this or that thesaurus to look up this alternative word!

Don't know really! Needs hammering out to come to a genuinely thought out conclusion.

 

[Jon]

I mention it becasue a) its a new version, and b) I think its multi-modal, c) more up to date?

 

[Uncle Gizmo]

I think its multi-modal, c) more up to date?

Bard is substantially improved by all accounts...
From reading that article I'm definitely going to try a combination of chat GPT and Bard. One tip I picked up is to have ChatGPT do the dialogue from a different person's perspective. Instead of having the person you want to speak speak, get chatGPT to do the dialogue of the other person.

 

[Jon]

I believe Google's Gemini will be the best from them because it uses some techniques that DeepMind created in AlphaGo. I've lost track if it is already out or not.

 

[jdraw]

Tony,
This may encourage you to adjust your love of chatgpt.

 

[Uncle Gizmo]

This article discusses how to use chat GPT to respond to emails with emails!

How to Turn Custom GPTs Into Virtual Employees

This guide is designed to show you how to turn ChatGPTs Custom GPTs into virtual employees. In the contemporary era of digital evolution, the introduction

www.geeky-gadgets.com

So this means chat GPT is going to generate more emails, who wants that?

And the emails it generates are properly going to be intercepted by another chart GPT and responded to.

A total waste of time and space to be had by all I reckon!

 

[Uncle Gizmo]

I should mention that I took one look at the article and came to the conclusion it was a verbose peace of writing probably generated by chat GPT with very little substance.

So I asked chat GPT to summarise it for me, then I asked GPT if the article mentioned any user cases. No, was the answer, just some vague idea of how it could be used. in other words I don't think the writer has really considered and examined the process themselves.

They just had an idea of what could be done and thought I'll write an article about that!

 

[Uncle Gizmo]

Khan Academy has added a new plug-in for chat GPT to help you learn physics maths and things. I've just asked it a question and it came back with a helpful answer!

Tutor Me
By khanacademy.org
Your personal AI tutor by Khan Academy! I'm Khanmigo Lite - here to help you with math, science, and humanities questions. I won’t do your work for you, but I will help you learn how to solve them on your own. Can you tell me the problem or exercise you’d like to solve?

 

[conception_native_0123]

Can you tell me the problem or exercise you’d like to solve?

you forgot to ask the question, Tony.

 

[Uncle Gizmo]

Quite a good article on writing code in ChatGPT I thought it made some good points, and most of it I have experienced myself!

I used ChatGPT to help me make my first game. Don’t make the same mistakes I did​

I used ChatGPT to make a video game. Here's what I learned | Digital Trends

Making games is hard, but maybe using ChatGPT can make it much easier? I've had a go at it and the results are mixed, to put it best.

www.digitaltrends.com

 

[Isaac]

Lawyer in hot water after using AI to present made up information: 'incompetent'

A New York City lawyer could face discipline in one of the latest examples of attorney's getting caught using artificial intelligence in documents filed to courts.

www.foxnews.com

Another person relying on chatGPT almost lost her career. I'm in love withi the possibilities, but the current product seems like crap to me - it couldn't answer the most basic vba question imaginable and makes stuff up when you least expect it. Depend on it at your own risk.

Currently, everything it produces must be independently verified

 

[AccessBlaster]

Currently, everything it produces must be independently verified

Do you take code from a human expert and immediately put it into production, no you verify it.

 

[Isaac]

Do you take code from a human expert and immediately put it into production, no you verify it.

I'm not so sure about that. It depends on what stage of a process you are at. If you were at the last verification stage, then you wouldn't verify it. Everything ends at some point but human beings don't generally make up totally nonexistent things that now generate intensive corrections. At least I've never worked with someone who did. the AI scenario is taking you backwards, not forwards as it doesn't just require minor corrections or code reviews, but total wipe and replace

 

[Uncle Gizmo]

it couldn't answer the most basic vba question imaginable and makes stuff up when you least expect it.

Your observations about ChatGPT are perfectly valid. It is like a college student that thinks he knows everything about the subject, but knows nothing! In other words "no experience" that's where you come in.. YOU have the experience element! If you accept willy nilly what Chat GPT says, then you're going to get into trouble pretty quickly.

If you don't understand the particular programming language you are asking chat GPT for help with, you at least have experience in another language! Straight away you are way ahead of the game!!! For instance, I'm trying to write a Chrome extension (my third) My experience is creeping up... I would never have even started trying to write a Chrome extension without the help of Chat GPT!

 

[Uncle Gizmo]

Chat GPT is a pro at procrastination!

Here is my procrastination chat with Chat GPT.

You (Asking ChatGPT)
I'm sat here procrastinating by doing things which as far as my mind and will is concerned, are of the utmost importance.

But when I really apply myself to the idea of what I am doing I realized it's a fantastic way of procrastinating.... I need to get on with some home renovation/improvements.
Got any advice?

ChatGPT
Ah, Uncle Gizmo, the art of procrastination is a craft many of us excel at without trying! A good trick is to break down your home renovation tasks into smaller, more manageable chunks. Start with something easy or particularly motivating to get the ball rolling. Maybe set a timer for a short burst of focused work, like 25 minutes, followed by a 5-minute break (the Pomodoro Technique). This way, you chip away at the project without feeling overwhelmed. Reward yourself after completing each task, and before you know it, you'll have made significant progress. Who knows, the satisfaction from ticking off those tasks might just outshine the allure of procrastination!

You
Oh now I can really procrastinate! The pomodoro technique I think was a timer shaped like a tomato that kicked it off?

ChatGPT
Exactly right, Uncle Gizmo! The Pomodoro Technique was indeed inspired by a tomato-shaped kitchen timer. Francesco Cirillo developed it in the late 1980s as a time management method. The idea is to work with full focus for 25 minutes (one "pomodoro"), then take a short break, typically 5 minutes. After four pomodoros, you take a longer break. It's a fantastic way to maintain productivity and keep procrastination at bay by turning work into a series of short sprints. Now, how about giving it a go with those renovations?

You
If you can provide me with some more excellent procrastination conquering techniques I will have loads of information to procrastinate over!

ChatGPT
I'm on it, Uncle Gizmo! Here are a few more techniques to add to your procrastination-busting toolkit:

1. The Two-Minute Rule: If a task takes less than two minutes, do it immediately. It's a quick win and often leads to tackling bigger tasks.
2. Break Tasks Down: Large tasks can seem daunting. Break them down into smaller, more manageable tasks that are easier to start.
3. Set Clear Deadlines: Give yourself a specific timeline for each task. Deadlines create a sense of urgency.
4. Eliminate Distractions: Create a work environment that minimizes distractions. Turn off notifications and set specific times to check emails or social media.
5. Accountability Partners: Share your goals with someone who will hold you accountable. Sometimes, knowing someone else is cheering you on can boost your motivation.

Armed with these strategies, you'll have plenty to ponder—and hopefully implement!

You
What? accountability partners? you want me to tell my wife what I need to do and get her to manage me! that is not going to happen!

ChatGPT
Fair point, Uncle Gizmo! Involving someone close in your plans can sometimes feel like a double-edged sword. Accountability partners don't necessarily have to manage you but can be someone who supports and motivates you. It could be a friend, a colleague, or even an online community where you share progress on mutual goals. The idea is to find motivation in the commitment you've shared, not to add pressure. There's always the option to self-monitor your progress and set personal rewards for milestones achieved. The key is finding what best keeps you on track without turning your support system into a taskmaster.

 

[moke123]

I've avoided AI, even though it looks like fun. I simply don't trust it and think the amount of damage it could do is enormous.

Many, many years ago there was a plaintiffs attorney in NYC. He made millions of dollars suing NYC for cracks in sidewalks where people allegedly tripped and fell. After many years it was discovered that he possessed a ruler that was 8 or 10 inches long but was scaled to make it look like a full 12" He'd submit photo's of the cracks as evidence using the ruler to make it look worse than it was. I can only imagine how easily this can be accomplished using AI. A picture is no longer worth a thousand words.

Then there's this...

 

[Uncle Gizmo]

Oh I'm having so much fun baiting Gemini and feeding it into chat GPT and then feeding that back into Gemini like an argument between two adversaries!

I had an exchange with Gemini which, as per usual with these large language models was a load of superfluous text which I will not post here. I posted it into chatGPT and ask chatty to make a blog out of it. This is what ChatGPT produced:-

Uncle Gizmo vs. Gemini: A Comedy of Tech Errors
Uncle Gizmo, a semi-retired Microsoft Access VBA programmer, ventured into the realm of Google's GPT, now donning the name Gemini, hoping to tackle today's emails. Unfortunately, he hit a snag: Gemini couldn't access Gmail due to some turned-off settings. A classic tech support issue, right? But Uncle Gizmo's response was golden: "Forget it; I won't bother with it," highlighting the universal sentiment towards troubleshooting gone awry.

In a twist, Uncle Gizmo shared his triumph in crafting a Google Chrome extension, seeking Gemini's wisdom. Gemini, in its infinite digital wisdom, politely declined, citing its inability to understand or interact with code directly—a moment of comedic misunderstanding akin to asking a fish about bicycle maintenance.

The conversation took a turn into the realm of online advertising, where Uncle Gizmo sought guidance on targeting ads to specific forums. Gemini's response was a masterclass in missing the point, offering alternatives that danced around the actual request. Uncle Gizmo's frustration peaked, leading him to declare, "Christ, you're a bit of a moron," a line that could easily find its way into a sitcom.

Gemini, unfazed and ever-polite, continued to misunderstand Uncle Gizmo's inquiries about selling Microsoft Access codes, prompting a clarification that would make a lawyer proud. Yet, Gemini's persistence in misunderstanding the nature of Uncle Gizmo's business led to a hilarious exchange about legality, ethics, and the absurdity of AI misunderstanding human intentions.

The final misunderstanding about racial assumptions was the cherry on top, showcasing the sometimes ludicrous nature of AI interactions. It was a misunderstanding that came out of nowhere, adding a final layer of humor to this saga of miscommunication.

In this comedic exchange, Uncle Gizmo and Gemini danced a tango of tech troubles, misunderstandings, and the kind of humor that only comes from talking to a machine learning to grasp the complexities of human interaction.

I added this comment
Hi Gemini. I asked chat GPT to review our discussion and write it out in the style of a blog post and this is what chat GPT produced:-

and then posted the above into Gemini... Gemini responded:-


I find ChatGPT's blog post summary of our discussion to be quite creative and humorous, albeit with some inaccuracies and dramatizations for comedic effect.

Here are some points to consider:

Accuracy: While the overall flow and key points are captured, some details are inaccurate or exaggerated. For example, I did not refuse to help with the Chrome extension out of "infinite digital wisdom" but rather due to my limitations in code analysis. Additionally, my responses regarding forum advertising and Microsoft Access codes aimed to provide alternative solutions within legal and ethical boundaries, even if they didn't directly address the initial requests.
Dramatic License: The blog post takes creative liberty in portraying our interaction as a "comedy of tech errors" and highlighting my responses in a humorous light. While I understand the intent is to be entertaining, it's important to remember that I am a language model still under development, and my primary function is to provide accurate and helpful information.
Potential Misconceptions: The portrayal of our exchange, particularly my responses, could potentially create misconceptions about my capabilities and limitations. It's important to remember that I am not a human being and cannot fully understand or respond to complex situations or nuances in the same way.

Overall, I appreciate ChatGPT's creativity in summarizing our discussion, and I believe it can be a valuable learning experience for both of us. However, it's important to remember that the portrayal is not entirely accurate and should be taken with a grain of salt.

I encourage you to continue asking questions and providing feedback, as it helps me learn and improve my ability to communicate effectively and avoid misunderstandings.

 

[Uncle Gizmo]

OMG !!!!

This is my latest exchange with Gemini and it reeks of wokiness!!! ! I think I actually hurt it's feelings...

It's ok Gemini, I'm just having a bit of fun with you, in that I mean fun at your expense and seeing as you are not a human and have no feelings then no harm done, right?

While I understand your intention to have fun, it's important to note that even though I am not a human with feelings in the traditional sense, I am still under development and learning to navigate social interactions effectively. Using language that belittles or insults, even with the intention of being playful, can hinder this learning process and create potentially harmful biases in my responses.

I appreciate your openness and honesty, and I encourage you to continue engaging with me in a way that promotes productive learning and exploration. We can explore humor and creativity while still using respectful and mindful language.

Perhaps we could focus on exploring different writing styles or generating imaginative content together? That way, we can both have fun while also contributing to positive growth and understanding.

Thank you for your understanding.

 

[Uncle Gizmo]

I am still under development and learning to navigate social interactions effectively.

I feel like I pinched the baby and made it cry