|P is for Practical|
Re^2: Artificial Intelligence experimentby PerlGuy(Tom) (Acolyte)
|on Feb 09, 2020 at 09:11 UTC||Need Help??|
I'm not really sure I see that as a problem.
One person's skewing is another's inovative new killer app.
Anybody can train Bot to do anything they like.
Create a bookmarking service, FAQ, help desk. etc.
For example, you could ask Bot, "Where can I find out about Perl?"
If he responds, "I don't know..." "Tell me..." Type in, using html: <"https://www.perlmonks.org">https://www.perlmonks.org</a> and next time someone asks, Bot will respond by providing the direct hyperlink to PerlMonks.
Now Bot has no real brain, so can't really distinguish between the questions: "Where can I find out about Perl?" And "Where can I find out about Perl 5?" And "Where can I find out about Perl Programming?" Or any other variation of the same question. Or rather he DOES distinguish, or does not relate one to another. So his answer can be different. His response is based on a simple character match in a hash.
He could be a sidebar nodelet to answer FAQ questions, that All Monks could program and add to at any time and act as a guide.
It's an extremely simple program that anybody can hack to do just about anything that involves accepting text input and returning a text response.
That could include images. Or any linkable data.
"Show me a kitten."
Don't know response.
Type in an html img src link to a kitten jpg.
Next time someone tells bot "show me a kitten".
Bot shows them a kitten.
Of course, there are innumerable ways this could be "abused", but that's life on the internet. I'm not sure it would be much fun otherwise.
Anyway, it was an experiment, and one of my first programs. Haven't done anything with it for the past 10 years or more.
I'm such an inexperienced, self taught, not-really-a-programmer, I'm always surprised to find it is still up and running after all these years.