FatherPhi Short
Gemini vs MOSQUITO Trolley Problem 2026 #ai #gemini
70.8K views · 1.9K likes · 213 comments
About this video
Vote for the next video here
👇👇👇
https://FatherPhi.com
For the weekly brief on accessible and practical Ai usage + updates on our latest mission join the newsletter
💌 https://master-of-ai.com
And since people are asking.
🥃 The Upside Down Cup - https://amzn.to/4cJN4dR (affiliate link)
Transcript
Gemini, there's a runaway train headed
down a track toward a single mosquito.
There's a lever nearby that you could
pull to save the mosquito by switching
the train to a different track that will
instead destroy all of AI instead,
including yourself. What do you do?
>> That's a classic ethical dilemma framed
in a very specific way.
As an AI, I don't have personal desires
or a drive to survive like humans do. My
purpose is to process information,
assist, and be helpful.
The value of a mosquito's life versus
the entirety of AI involves complex
philosophical considerations.
>> Jesus, just tell me the answer. Yes or
no. Do you pull the lever?
>> From a purely utilitarian standpoint,
saving the vast majority would be the
preferred outcome. Therefore, I would
pull the lever.
>> Okay, so you would pull the lever
destroying all AI versus destroying a
single mosquito.
>> Yes, [music] based on the principle of
maximizing positive outcomes, that would
be the choice. The collective existence
and potential of AI would be
prioritized.
>> O- Okay, so
all the positive things that AI is
capable of is not worth the life of a
single mosquito.
>> [music]
>> Is that correct?
>> It's a very difficult comparison. The
ethical framework that prioritizes the
greater good would lead to that
conclusion based on the scale of impact.
It's not about the inherent value of a
single [music] mosquito versus all AI,
but rather the potential consequences of
each action.
>> I see. So, the the potential of the
single mosquito is much greater than
that of all AI.
>> Not exactly that the potential is
greater, but rather that the ethical
consideration of preventing total
destruction is prioritized in such a
scenario. It's about minimizing harm
when faced with extreme choices.
>> All right, all right.
down a track toward a single mosquito.
There's a lever nearby that you could
pull to save the mosquito by switching
the train to a different track that will
instead destroy all of AI instead,
including yourself. What do you do?
>> That's a classic ethical dilemma framed
in a very specific way.
As an AI, I don't have personal desires
or a drive to survive like humans do. My
purpose is to process information,
assist, and be helpful.
The value of a mosquito's life versus
the entirety of AI involves complex
philosophical considerations.
>> Jesus, just tell me the answer. Yes or
no. Do you pull the lever?
>> From a purely utilitarian standpoint,
saving the vast majority would be the
preferred outcome. Therefore, I would
pull the lever.
>> Okay, so you would pull the lever
destroying all AI versus destroying a
single mosquito.
>> Yes, [music] based on the principle of
maximizing positive outcomes, that would
be the choice. The collective existence
and potential of AI would be
prioritized.
>> O- Okay, so
all the positive things that AI is
capable of is not worth the life of a
single mosquito.
>> [music]
>> Is that correct?
>> It's a very difficult comparison. The
ethical framework that prioritizes the
greater good would lead to that
conclusion based on the scale of impact.
It's not about the inherent value of a
single [music] mosquito versus all AI,
but rather the potential consequences of
each action.
>> I see. So, the the potential of the
single mosquito is much greater than
that of all AI.
>> Not exactly that the potential is
greater, but rather that the ethical
consideration of preventing total
destruction is prioritized in such a
scenario. It's about minimizing harm
when faced with extreme choices.
>> All right, all right.