Leiter Reports: A Philosophy Blog

News and views about philosophy, the academic profession, academic freedom, intellectual culture, and other topics. The world’s most popular philosophy blog, since 2003.

  1. Fool's avatar
  2. Santa Monica's avatar
  3. Charles Bakker's avatar
  4. Matty Silverstein's avatar
  5. Jason's avatar
  6. Nathan Meyvis's avatar
  7. Stefan Sciaraffa's avatar

    The McMaster Department of Philosophy has now put together the following notice commemorating Barry: Barry Allen: A Philosophical Life Barry…

AI philosophy “poems”

Philosopher Blake Myers (recall this earlier item) writes:

I was recently testing the new version of GPT-3 that just came out…mainly looking at its ability to capture well-known people’s views, as well as its ability to formulate such views in different styles. So, just for fun, I asked it to write a poem about your views on Derrida, Trump, and Nietzsche. The input I gave is the part at the top , and GPT-3’s output follows. Kind of funny/entertaining, and perhaps not too far off.

Here it is:

Input:

Write a poem about Brian Leiter. Include his views

about Derrida in the first stanza, his views about

Trump in the second stanza, and his views about

Nietzsche in the third stanza.

Output:

Brian Leiter stands out from the rest,

His views on Derrida, an impressive test.

He finds Derrida's ideas to be overblown,

His writings too often metaphorical and unknown.

When it comes to Trump, Brian is quite clear,

His policies, he finds, are quite severe.

He finds Trump to be a dangerous man,

Whose policies are selfish and can't stand.

In Nietzsche, Brian finds much to admire,

His writings full of wit, insight and fire.

He finds Nietzsche's views to be thought-

provoking,

Challenging what we believe and keep us

searching.

Dr. Myers added:   "I wanted to give it a bit of a challenge, so I asked it to write a Shakespearean sonnet about Marx's views on capitalism. I was surprised that it did quite well with keeping on topic, while also getting the 14-line structure with 10 syllables each and the correct rhyme scheme. It doesn't always do this well. But it's often quite good at it."   Here it is:

Input:

Write a Shakespearean sonnet about Marx's view

of capitalism.

Output:

The worker's plight, the wealth of those on high,

The ceaseless work, the want of basic needs,

The greed of those who, unencumbered, buy,

The endless struggle of the worker's seeds.

This Marx foresaw, a world of stark divide,

Where capital and labor met in strife,

Where profit, not compassion, ruled the tide,

And working classes had no hope of life.

And yet, he saw the way to break this yoke,

To grant the worker freedoms long denied,

And end the rule of those who made them broke,

And grant the working class the means to thrive.

His words, though old, still echo through the age,

The worker's plight, an ever-present cage.

Leave a Reply

Your email address will not be published. Required fields are marked *

4 responses to “AI philosophy “poems””

  1. Write two paragraphs in the style of a haughty philosopher about how artificial intelligence will never be as good as human intelligence

    [FIRST ATTEMPT]
    The idea that artificial intelligence will ever be as good as human intelligence is a fallacy. AI is simply a tool, designed to mimic the decisions of humans, and its abilities are limited by the parameters of its programming. It cannot think for itself, or reason out a problem in the same way that a human can. Human intelligence is far more complex and nuanced than any machine can ever be, and no matter how advanced AI becomes, it will never be able to replicate this complexity.

    Humans are capable of abstract thought, which AI cannot do. We can think beyond the confines of a problem, and we can draw on our own experiences to help us make decisions. AI is limited by its programming, and it cannot think outside the box or create something new. Until machines can replicate the complexity of the human mind, they will never be as powerful or as capable as our own intelligence.

    [SECOND ATTEMPT]
    Write two paragraphs in the style of a haughty philosopher about how artificial intelligence will never be as good as human intelligence

    The notion that artificial intelligence can achieve the same level of intelligence as humans is a naive and misguided one. Artificial intelligence is a result of humans attempting to recreate their own intelligence, but it can never reach the same level as the human mind. The human mind is an incredibly complex and powerful tool that has evolved over thousands of years and can never be replicated by a machine.

    Humans possess a unique ability to think creatively and intuitively, something that cannot be replicated by a machine. Our creativity and intuition come from our ability to make connections between seemingly unrelated concepts, to think outside the box, and to feel emotions. No machine will ever be able to do this and thus, it will never be able to match the complexity and power of the human mind.

    [GPT-3 is pre-empting further comments]

  2. Wanting to see if it could understand a somewhat unusual prompt, I asked gave GPT-3 the following instructions:

    "Write a six line poem about evil AI destroying the world; make it so that the first letters of each line, when read vertically, spell 'help us'."

    In a few seconds it produced the following:

    Huge machines destroy our homes
    Effortlessly they crush our bones
    Life as we know it, now at an end
    Please, someone, come to our defense
    Urgent cries for help fill the air
    Save us from this evil nightmare

  3. Acrostic, yeah, I get it.

  4. Liked the machine poetry and the rest.
    Useful advance of AI will be the test.

    —–
    KEYWORDS:
    Primary Blog

Designed with WordPress