Can AI Be Wrong?

Can AI be wrong is a thought of when you repeatedly use AI.

Now. I love AI and I think it is going to have a place in society whether we like it or not. It can not be forgotten about.

Do I use it. Yes I do. I use ChatGPT. Why?

it saves time
it takes a large amount of data, analyses it and then makes it more manageable
it can give ideas
it is impartial (to some extent). So it is like "here is the data" regardless if it goes against your thoughts

I primarily use AI for planning which it has been very good at.

Can AI be wrong...or can it give different data?

AI seems to be built up the learning process of asking questions, generating answers and reevaluating information. It also mines the Internet.

But it does have a few draw backs for gathering info:

It is not constantly mining the Internet. So information is based upon when it was last updated.
It doesn't always give the definitive answer. It gives you information and it is upto you to decide which one is relevant
unless asked, it doesnt give references

Now what I have noticed from what people have shown online is that it:

Gives you information that is already there, that if you were in the field you should already know.

So, in my example of the Green Gadget Guru you saw the information that AI gave about how to turn $100 into an online business that can generate $1000.

People were astounded. It made front pages of online media. But, if you were already knew about online selling/ marketing etc then the ideas that AI generated were kinda normal if not obvious and have been touted online for a very long time:

Freelancing Services
Dropshipping
Affiliate Marketing
Online Courses or Ebooks
Social Media Management
Digital Marketing Services
Stock Photography
Virtual Assistance
Create and Sell Apps
Online Consultation

Forbes gave a list of 15 mistakes that AI needs to avoid. But for it to learn does it have to make mistakes and then correct for them? In one of the Forbes list they stated a Stanford quote:

“AI systems are being used in the service of disinformation on the internet, giving them the potential to become a threat to democracy and a tool for fascism. From deepfake videos to online bots manipulating public discourse by feigning consensus and spreading fake news, there is the danger of AI systems undermining social trust. The technology can be co-opted by criminals, rogue states, ideological extremists, or simply special interest groups, to manipulate people for economic gain or political advantage.”

Now this seems all. WOW! Slow down here Jasonera. But in my experience I have found that you need to be extreamly specific in asking questions, like when we went through how to make an ebook with AI.

I wanted to know about websites that use Amazon Affiliates and have been successful. Here is the answer:

"Real-Life Examples of Amazon Associates Success

1. Tech Reviewer and Blogger: John's Gadgets Galore

John, a tech enthusiast and blogger, runs a website called "John's Gadgets Galore," where he reviews the latest gadgets and electronics. By joining Amazon Associates, John strategically places affiliate links within his product reviews. When readers click on these links and make a purchase, John earns a commission. Given the wide range of tech products available on Amazon, John has successfully turned his passion for gadgets into a revenue stream.

2. Fitness Influencer: Sarah's Wellness Hub

Sarah, a fitness influencer with a significant following on social media, curates workout gear recommendations on her blog and Instagram. By incorporating Amazon affiliate links into her fitness equipment reviews and workout routine posts, Sarah earns commissions when her audience purchases recommended products. The extensive selection on Amazon allows her to cater to various fitness levels and preferences, enhancing the user experience".

Cool, that gave me an outline to start working. However. I searched everywhere online for these websites: Johns Gadgets Galore and Sarahs Wellness Hub. Could not find them anywhere.

Then I asked Chat to give me the addresses of these, because I want some references. Also after an hour of searching I was concerned I was missing something:

"I'm sorry for any confusion, but the examples provided were created for illustrative purposes, and as such, they do not represent real websites or content creators".

So even though the question asked for real world examples, Chat gave back examples of people if they did create certain websites for Amazon affiliates.

Can you use trust AI then?

Of course. But you have to know your subject and be able to catch things that might be missed by people who do not know the subject.

But this is not an AI issue either. Even WIKI has issues, but people still use it as a source of complete fact even though it is user generated. Here's from Wiki themselves:

"In 2007, Michael Gorman, former president of the American Library Association (ALA) stated in an Encyclopædia Britannica blog that "A professor who encourages the use of Wikipedia is the intellectual equivalent of a dietician who recommends a steady diet of Big Macs with everything".
Academics have also criticized Wikipedia for its perceived failure as a reliable source and because Wikipedia editors may have no expertise, competence, or credentials in the topics on which they contribute
"The experts found Wikipedia's articles to be more credible than the non-experts. This suggests that the accuracy of Wikipedia is high. However, the results should not be seen as support for Wikipedia as a totally reliable resource as, according to the experts, 13 percent of the articles contain mistakes""

AI is cool. But take a step back. Figure out what you are trying to find and then reference it with people and text that are also in the know. Hopefully both will align, but if they don't you can adjust.

For more info on eProduct selling, check out the Jasonera blog.