I'm in Love with ChatGPT

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​

www.digitaltrends.com

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

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 www.digitaltrends.com
 
www.foxnews.com

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 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
 
Isaac said:
Currently, everything it produces must be independently verified
Click to expand...
Do you take code from a human expert and immediately put it into production, no you verify it.
 
AccessBlaster said:
Do you take code from a human expert and immediately put it into production, no you verify it.
Click to expand...

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
 
Isaac said:
it couldn't answer the most basic vba question imaginable and makes stuff up when you least expect it.
Click to expand...
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!
 
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.
 
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...

 
  • Wow
Reactions: Jon
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.
 
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.
 
What AI can do for historians

Chat GPT finding a niche in historical document analysis.

There's A link to the article below. The article is very good, very well written.

Chat GPT summary of article:-

ChatGPT
Josh Dzieza's article for The Verge explores how AI, particularly large language models like ChatGPT, is starting to impact historical research. Historian Mark Humphries, initially skeptical, found AI invaluable in correcting and translating historical documents, sparking interest in its broader application for analyzing digitized archives. This has the potential to revolutionize historical research by reducing the manual effort needed to sift through vast amounts of data. However, there's caution in the field due to AI's propensity for fabricating facts and inherent biases. The piece also mentions the excitement around AI at the American Historical Association's annual meeting, showcasing projects where AI aids in searching historic maps and analyzing archival photos. Humphries developed an AI system named HistoryPearl to assist his research on 18th-century fur traders, overcoming challenges related to AI's understanding of historical language and context. The article underscores the dual nature of AI in history—its transformative promise and the challenges of ensuring accuracy and relevance.

www.theverge.com

What AI can do for historians

It turns out that large language models make surprisingly good research assistants for historians. Can the future of AI help reconstruct the past?
www.theverge.com www.theverge.com
 
Last edited:
I asked chat GPT to explain how the process employed by the researcher might work:-

When we talk about using "different versions of customized ChatGPT" created by a researcher for iterative analysis, we're essentially discussing a multi-stage AI pipeline. Each stage is tailored for a specific aspect of the analysis or processing task, customized through fine-tuning or specific prompt engineering to handle different parts of the research process. Here’s how such a setup might look:

### 1. **Fine-Tuning Multiple Models**
Initially, the researcher would create several specialized versions of ChatGPT, each fine-tuned for different tasks. For example, one might be trained to correct historical language or interpret old scripts, another to translate, and yet another to extract specific types of information (like names, dates, or events) from the corrected texts.

### 2. **Setting Up a Python Environment**
After ensuring Python is installed and the virtual environment is ready, the researcher installs necessary libraries, most importantly `openai` for API interactions.

```python
pip install openai
```

### 3. **Authenticating and Configuring API Calls**
The researcher authenticates with the OpenAI API using their key, setting it up securely in their script.

```python
import openai
openai.api_key = 'your_api_key_here'
```

### 4. **Creating a Pipeline of Tasks**
Here's where the system becomes more sophisticated. The researcher writes a Python script that processes the material through a sequence of these customized ChatGPT models, each serving a different role in the analysis. This might involve:

- **Initial Processing:** Sending the material to the first ChatGPT model specialized in transcribing or correcting old scripts.
- **Translation and Interpretation:** Passing the corrected text to another model for translation or further interpretation.
- **Extraction of Information:** Using another fine-tuned model to extract specific data points from the text.

### 5. **Iterative Querying**
The process involves iterative querying, where the output of one model serves as the input for the next. This could be automated in a loop or a series of function calls within the Python script, managing data flow between different AI models.

```python
# Example pseudocode for a simplified process
corrected_text = transcribe_and_correct(original_text)
translated_text = translate_text(corrected_text)
extracted_data = extract_information(translated_text)
```

### 6. **Handling and Analyzing Outputs**
The script collects outputs from each stage, which the researcher can then analyze. This multi-step output can offer insights that are more nuanced and tailored to the specific needs of the historical research being conducted.

### 7. **Refinement and Iteration**
Based on the initial results, the researcher may refine their models, adjust their prompts, or tweak the sequence of tasks to improve accuracy and relevance of the outputs.

This revised approach acknowledges the layered complexity of historical document analysis, leveraging AI's potential to perform a series of specialized tasks that build upon one another. It’s a bit like assembling a team of experts, each with their own niche, to collaboratively work through the intricacies of historical texts, except here, the experts are AI models trained for specific facets of the task.
 
See AI Created Videos. Indistinguishable from reality ...

I follow this chap Wes Roth. He talks a lot of sense and in a comprehensible manor.

Observations about AI are well worth listening to see video below:-


 
I've been following these guys for over a year. They talk a lot of sense.

In this YouTube meeting they discuss the future of AI.... The future being "later this YEAR" ... There's a good chance a fundamental shift in knowledge and robotics will occur in 2024.

If you thought the LLM ChatGPT was fascinating, wait till you see embodied AI ..

www.youtube.com

BOMBSHELL Announcement from Figure Robotics!

Herbert Ong, Cern Basher, Scott Walter and I discuss the massive fund raising news from Figure Robotics, and how this changes the world of embodied AI--yet a...
www.youtube.com www.youtube.com
 
Last week, my boss asked me to look into an email issue that our company was having. Lots of details that I wont bore you with, but she figured since I knew how to automate Outlook with Access that I would be able to figure this out.

I took that issues and presented them to Chatty who gave me about 6 explanations for the issues we were experiencing. I took the one that made the most sense and even though I guessed wrong :rolleyes: , it made the lightbulb come on with the OL Exchange team who fixed the real problem.

My company's VP thinks I am a genius and my boss looks like a talented manager for giving this to the right person... I suppose I should tell them the truth, but who am I to argue with the boss??
 
You must log in or register to reply here.

Similar threads

jwcolby54
Using ChatGPT as a personal editor
Replies
0
Views
700
jwcolby54
jwcolby54
K
ChatGPT vs Atari
Replies
0
Views
718
KitaYama
K
GPGeorge
Leveraging ChatGPT for Incremental Development in Microsoft Access with John W Colby
Replies
4
Views
641
GPGeorge
GPGeorge
Uncle Gizmo
8hrs Time Saved - Uncle + AI (ChatGPT)
Replies
5
Views
840
Isaac
Isaac
Gasman
ChatGPT
Replies
13
Views
482
Isaac
Isaac

Users who are viewing this thread

Total: 1 (members: 0, guests: 1)
Back
Top Bottom