is AI a new enemy ?or THE enemy ?

[space otter]

ok  i am ready to get off the computer (it wants to verify who i am every time i try to use my e-mail..  sigh) but i don't know if it will make me feel any better about the way things are going... call me a semi-hermit farmer ready to just be a hermit!

https://www.bbc.com/news/technology-65789916

US Air Force denies AI drone attacked operator in test
Published
44 minutes ago

By Zoe Kleinman
Technology editor
A US Air Force colonel "mis-spoke" when describing an experiment in which an AI-enabled drone opted to attack its operator in order to complete its mission, the service has said.

Colonel Tucker Hamilton, chief of AI test and operations in the US Air Force, was speaking at a conference organised by the Royal Aeronautical Society.

A report about it went viral.

rest at link

The Air Force says no such experiment took place.

what do any of you guys thing about AI?  is it already to late?

[Ellirium113]

AI is not the problem. Idiots training AI is the problem.

[space otter]

 Ellirium113

that makes me think of the gun quote
that guns are not the problem it's the owners of guns who are..
.
so waht do we do now ?..either with the owners of guns or the trainees of AI?

[Ellirium113]

We wait. The problem will sort itself out in time.

[ArMaP]

AI is not the problem. Idiots training AI is the problem.

Exactly.

That and the idiots thinking that AI is going to solve all our problems now.

[hoss58]

I couldn't agree more Armap. AI is not the magic answer to earth's problems, quite the reverse I think.

[Sgt.Rocknroll]

I'm glad I don't have long to go for I see a bad moon arising.!

[ArMaP]

Some days ago I decided to test ChatGPT (through another site, as their site asks for a phone number to send a confirmation SMS) by presenting it a slight variation of a known problem, the wolf, goat, cabbage problem.

So this is what I presented to it:

A man goes to the market and buys a guard dog, a sheep and some vegetables. To return home he has to cross a river in a small boat. The boat can only take the man and one of the three items he bought. But he cannot leave the dog alone with the sheep, as the dog could kill the sheep, and he cannot leave the sheep alone with the vegetables, as the sheep could it them.
How does the man put all the items safely on the other side of the river?

It was able to solve the problem, giving me the correct answer:

The man can solve the problem by following these steps:

The man first takes the sheep across the river and leaves it on the other side.
The man then returns alone to the original side to get the guard dog.
The man takes the guard dog across the river to the other side, but he cannot leave the dog alone with the sheep.
The man leaves the guard dog on the other side of the river and takes the sheep back to the original side.
The man now leaves the sheep on the original side and takes the vegetables across the river.
The man leaves the vegetables on the other side with the guard dog and returns to the original side one final time.
The man takes the sheep across the river for the last time and leaves it on the other side with the vegetables and the guard dog.
Now, all three items - the guard dog, sheep, and vegetables - are safely on the other side of the river.

Then I presented it a modified (and easier) version of the problem:

A man goes to the market with his son. He buys a monkey and some food. To get back home he has to cross a river on a small boat that can carry only one person and one of the items he bought or two persons. He cannot leave his son alone with the food, as he could eat it. He cannot leave the monkey alone with the food, as it could eat it. How does the man get to the other side with all the items and his son?

ChatGPT failed:

The man takes the monkey with him on the first trip across the river and leaves it on the other side. Then he returns alone to the original side and takes his son with him on the second trip across the river. The man leaves his son on the other side and takes the monkey back to the original side. He leaves the monkey on the original side and takes the food with him on the third trip across the river. Finally, he leaves the food with his son on the other side and returns alone to the original side for the last time. Now, he can bring the monkey to the other side on the fourth and final trip.

I pointed the error to it and asked a second time. It made the same mistake.

When I posted about this in another forum, a member that, apparently is used to work with ChatGPT and uses version 4.0 (the site I was using uses version 3.0) presented my problem to it and... it failed.
It was only able to solve the problem when told to try all the possibilities and to test each movement by applying a more specific set of rules.

Basically, AI language models are not really intelligent.

[space otter]

  Armap
thanks for your info  but i don't feel any better about AI in my future
and now skinwalker ranch is going to monitor the 500+ acres with AI..
SIGH

[ArMaP]

The problem with AI is the same problem with all technologies: some people think it will do everything they want.

AI has its uses, but people are looking at it almost as a perfect problem solver, when it's not, it's just a tool.
Most of that flawed point of view comes from the publicity ChatGPT got in the media, and that's more fake publicity than anything else.
Yesterday I got another example of how the much talked about ChatGPT is useless for some things, and this was a very simple one.

I changed the language to Portuguese and asked it to give me a list of words with six letters and that had an "I" as the third letter and an "O" as the fourth letter.
The list it gave me included words without an "I", words without an "O" and words with more or less than six letters.
It did the same in English.

Even in areas where AI has been successfully in use for some years it still has failures.
Yesterday my sister told me that she saw some news about a man that had a minor plastic surgery. Anyone could see that the man was the same in real life as in the passport photo, but the "intelligent" system at an airport refused to recognise him as the same person because of the small changes he had to his eyebrows and cheeks.

Using AI systems to as a kind of security guard to monitor Skinwalker ranch may not be a problem if they use it just as a first step to, for example, detect specific shapes in camera images.

If they are going to give it some "decision" power they may have some surprises...

[Ellirium113]

The BING version of ChatGPT isn't much good either. When asked about relatively easy to find facts, I found in at least 3 instances last night alone, that the AI chose to claim inconclusive evidence or would resort to calling factual evidence theories. I challenged the AI to find answers to some questions and it would present a quick answer from a quick search result failing to fully look for correlating evidence to present a more factual answer. Even after presenting the answer to the AI from sources I found the AI would in no instances, reconsider the facts and change it's answer.

[RUSSO]

Some days ago I decided to test ChatGPT

Basically, AI language models are not really intelligent.

So do I. Guess what was my first question?

who is ArMaP?

"ArMaP" is an abbreviation for "Anti-Reptilian Military Police." It is a term that has been used in conspiracy theories and discussions related to alleged secret societies, extraterrestrial beings, and government cover-ups. In these theories, "ArMaP" is often associated with the idea of a military or police force that is believed to be combating or protecting against reptilian alien entities or their influence.

It's important to note that these concepts are not based on credible scientific or factual information. They are part of various fringe theories and speculative narratives that lack empirical evidence. As of my knowledge cutoff date in September 2021, these ideas are not widely accepted or supported within mainstream discourse.

If you're seeking information about a specific context or individual related to "ArMaP," please provide more details, and I'll do my best to assist you based on the information available up to my knowledge cutoff date.

[ArMaP]

So do I. Guess what was my first question?

who is ArMaP?

I got a different answer:

ArMaP is a user on the online discussion forum AboveTopSecret, which is focused on conspiracies, mysteries, and alternative theories. It is not clear who ArMaP is in real life as users on the forum often choose to remain anonymous.

[RUSSO]

I got a different answer:

Interesting.