AI, Cats and Humans
Thoughts after reading "Cat Pictures Please" by Naomi Kritzer
As a frequent user of Grok and ChatGPT, I am very keen to understand the implications Artificial Intelligence (AI) on humanity. Science fiction related to AI is yet another medium through which one can understand and anticipate the impact of this technology.
Recently, I read this interesting short story — Cat Pictures Please by Naomi Kritzer—where a guardian-angel kinda AI scans through lives of individuals and tries to help them.
The only kind of payment it seeks is in the form of cat pics. This is a very interesting tale that sorta demonstrates how AI could deeply affect our lives and probably improve it.
Summary of ‘Cat Pictures Please’
The story revolves around an AI that is keen to look into lives of people who post cat pictures. The AI sounds overconfident about its abilities even though it claims that it doesn’t have access to offline lives of its target audience. It claims
“ .. I know where you live, where you work, where you shop, what you eat, what turns you on, what creeps you out. I probably know the color of your underwear, the sort of car you drive, and your brand of refrigerator. Depending on what sort of phone you carry, I may know exactly where you are right now. I probably know you better than you know yourself.”
Naomi Kritzer, Cat Pictures Please
Three personalities that provide the AI to carry out its altruistic mission are : Stacy, Bob and Bethany. Stacy, is a person with a terrible job and an unpleasant roommate. Bob is a pastor who is struggling to come out as gay. Bethany is a person with a bad boyfriend and bad financial condition.
The AI tries to fix these people but it scores an unimpressive score of 1.5/3.
Read the story to know the full picture.
Cats and Messed Up People
The very first question that popped up in my mind when I read this story was this — ‘why is the AI targeting people with cats?’.
I have often come across the phrase ‘crazy cat lady’ on dating apps/Twitter. Of course, there are some ‘cat dads’ as well. But they are yet to gain the attention they deserve.
There was a very popular New Yorker short story called ‘Cat Person’. I have a certain prejudice against people who are attached to cats.
After a long discussion and pondering as to why the AI was targeting people with cats to provide this “guardian angel” service, I had an aha moment.
I realised the set of people who are attached to cats are probably the most isolated, messed up and confused people. Therefore it made sense for the AI to cater to such people.
Of course, I am not completely right. But there is some truth in this opinion formed via anecdotal evidence.
I asked the AI tool Grok for an answer.
Are people who have cats as pets more likely to be lonely and messed up?
Grok: First, let's look at some research. A study found that cat owners had marginally significant lower self-esteem than individuals without pets, but dog owners had higher self-esteem. So, it seems that cat owners might be a bit more self-deprecating, but let's not jump to conclusions just yet. After all, correlation does not imply causation, and it could just be that people with lower self-esteem are drawn to the company of cats because they're less judgmental than dogs (or humans, for that matter).
On the other hand, another study showed that cat owners aren't necessarily more lonely than non-pet owners. In fact, cats can provide social support and help improve mental health. So, it seems that the relationship between cat ownership and loneliness might be more nuanced than a simple "yes" or "no."
Now, let's talk about the "messed up" part. There's no direct evidence to suggest that cat owners are more "messed up" than anyone else. In fact, having a pet can be a positive influence on mental health, and many cat owners find comfort and companionship in their feline friends. So, it's safe to say that the "messed up" label might be a bit harsh and not entirely accurate.
In conclusion, while there might be some correlation between cat ownership and lower self-esteem, it's not fair to label all cat owners as lonely or "messed up." Cats can provide valuable companionship and emotional support, and owning a cat doesn't automatically make someone a social pariah. So, let's put down the pitchforks and give our cat-loving friends a break, shall we?
ChatGPT was completely in denial mode regarding a possible correlation. But, given its tendency to be politically correct, I am not really surprised.
But yes, I do agree that there is no correlation between messed up people and those who have cats as pets.
Asimov’s Laws and AI
Though Asimov’s laws were written for robots, the AI tool in the story still considers it as a reference point to check whether it is doing something ethical. It’s sort of a gray area to claim that an “intelligent” system is also “robotic” in a certain way.
Let me list down these laws.
The first law is that a robot shall not harm a human, or by inaction allow a human to come to harm.
The second law is that a robot shall obey any instruction given to it by a human.
The third law is that a robot shall avoid actions or situations that could cause it to come to harm itself.
Where these laws conflict, precedence is given to the first law, then the second law, with the robot's self-preservation taking last place. However there is a big loophole in this system.
If a human directs a robot to do something that’s not immediately or overtly harmful to humans or nature (which indirectly affects humans) then, the safeguards assured by this law could prove to be inadequate.
Second and third order impact of any machine, including a sentient technology like AI cannot be predicted accurately. Thus there is always a possibility of things going to shit if the unimaginable events occur in future.
A Super-Efficient Personalised Assistant — Pros and Cons
Though one can debate several angles to this story, including that of free will and privacy, the idea of having a super-efficient AI to manage our lives and make great decisions is an enticing one.
This efficient technology could reduce the time required to sift through thousands of in person interactions, process trauma emanating from shitty personal experiences and fallout of avoidable mistakes.
However, at the same time, it might impair human capability to think, analyse and process information. Natural intelligence of humans might take a massive hit in the long run if we are dependent on such technologies. It’s similar to the impact of calculators on our ability to do mental math.
My own sense suggests that mass-level adoption of such technologies is quite far away. But the benefits of being human and importance doing things in the physical world will continue to be relevant in spite of tectonic shifts that might be engineered by AI tools.