Instigator / Pro
4
1581
rating
38
debates
64.47%
won
Topic
#3851

You pick the topic vs. GPT-3

Status
Finished

The debate is finished. The distribution of the voting points and the winner are presented below.

Winner & statistics
Better arguments
0
6
Better sources
2
4
Better legibility
1
2
Better conduct
1
1

After 2 votes and with 9 points ahead, the winner is...

Novice_II
Tags
Parameters
Publication date
Last updated date
Type
Standard
Number of rounds
3
Time for argument
One week
Max argument characters
20,000
Voting period
One month
Point system
Multiple criterions
Voting system
Open
Contender / Con
13
1890
rating
98
debates
93.37%
won
Description

Full Disclosure: I will not being writing Pro's arguments. My goal with this debate is to test the capabilities of GPT-3 in the field of debate. Unrated as GPT-3's ability should not affect my own Elo.

Rules: Please make the topic somewhat defensible. I suspect that based on how GPT was trained, it will perform best on topics that have been seriously argued on the Internet in the past.
Voters should treat this as a normal debate for their RFDs, but criticisms and insights on GPT's process are welcome in the comments.

Round 1
Pro
#1
As per the rules, GPT-3 will write Pro's arguments. The GPT-3's design requires a prompt input, which will be bolded to differentiate from generated text in the following rounds.

The topic will be selected by Con.
Con
#2
The topic will be: THBT Kant's Categorical Imperative is inconsistent.

Terms:
Inconsistent: lacking in consistency
Round 2
Pro
#3
Write a long formal debate from the position of Pro in favor of the claim "Kant's Categorical Imperative is inconsistent" using as many arguments as possible.
Pro:
Kant's Categorical Imperative is inconsistent. It states that we should always act in such a way that our actions can be willed as universal law, but it also says that we should never act in such a way that we treat other people as means to our ends. However, it is often the case that we cannot achieve our goals without using other people as means to our ends. For instance, if I want to get a job, I need to impress my potential employer in an interview. But in order to do that, I need to use them as a means to my end of getting the job. I cannot will my action of impressing my potential employer as a universal law, because not everyone can do that - some people are just naturally more impressive than others. Therefore, Kant's Categorical Imperative is inconsistent.

In addition, the Categorical Imperative is self-defeating. Kant says that we should never act in such a way that we treat other people as means to our ends. But if we never treat other people as means to our ends, then we will never achieve our goals. We will never get jobs, because we will never be able to use other people as means to our end of getting a job. We will never be able to have relationships, because we will never be able to use other people as means to our end of having a relationship. We will never be able to have children, because we will never be able to use other people as means to our end of having children. In short, we will never be able to achieve anything, because we will never be able to use other people as means to our ends. Therefore, the Categorical Imperative is self-defeating.
Con
#4
Overview
  • This debate is very straightforward. Pro has the burden of proof, and the proposition in question is "[k]ant's Categorical Imperative is inconsistent." Therefore, pro must simply demonstrate the logical contradiction within Kant's categorical imperative. In pro's first round, there is no indication that this was done, so if I were to contain my argument to this overview alone, and discard the rest of pro's case, the debate will remain in favor of the contender. 

  • "A contradiction is a logical incompatibility between two or more statements or propositions...[t]his means that one of those statements must be false; they cannot both be true at the same time and in the same manner. The logical form of a simple contradiction is "Statement + negation of that statement." Stated in symbolic form, this would be: 'p and not p', or 'p•~p'"

  • "The categorical imperative is the centerpiece of Kant’s ethical theory. The term categorical imperative basically means “absolute command.” Kant is referring to, what he sees as, an exceptionless obligation to perform the action dictated by the categorical imperative. Perhaps the best way to understand the categorical imperative is to look at how Kant used it. It was his means for determining which action was the morally correct action in any given circumstance."
  • In the categorical imperative, there are three formulations
    1. The Principle of the Law of Nature
      1. "We should act as if our actions will become a universal law of nature. In other words, if anyone else were to be in similar circumstances to ours, they would be required to act in exactly the same manner."
    2. The Principle of Ends
      1. "[W]e should always treat human beings, including ourselves, as if they are an end in and of themselves, and never only as means to an end. In other words, we should respect and value others, and not simply use or manipulate them to accomplish our own purposes"
    3. The Principle of Autonomy
      1. "We are not dependent upon others to tell us what is right and wrong, but that we are free and able to discover this for ourselves through the use of reason" 

Rebuttal(s)
  • Remember, pro bears the burden in this debate, and con holds none. Now that we understand the categorical imperative, it is clear to see that pro has failed to show any logical contradiction within it. 

Claim 1
However, it is often the case that we cannot achieve our goals without using other people as means to our ends. 
  • This does not even attempt to produce a contradiction. Kant never says we should achieve all our goals in "The Principle of the Law of Nature." Only we should act in a manner as if our actions would become a universal law by which all people acted. 
  • Secondly, pro clearly misunderstands "The Principle of Ends." Kant argues that we should not "manipulate [others] to accomplish our own purposes." This has to do with moral virtue underlying our actions. If you can't pursue a career without acting with moral virtue Kant would simply argue that you ought not act in that manner and you should seek to impress your employer in an honest and virtuous manner. 
  • Overall, no logical form of a contradiction (P and not P), and no semblance of a contradiction here. 

Claim 2
...the Categorical Imperative is self-defeating. Kant says that we should never act in such a way that we treat other people as means to our ends. But if we never treat other people as means to our ends, then we will never achieve our goals.
  • This is just a repeat of the first claim in different words. First, this is not self-defeating because there is no internal contradiction in any of the propositions. Just because you think something sounds bad does not mean it is inconsistent. 
  • Second Kant never said we should or ought to achieve all of our goals. This is just a strawman. 
  • Third, this misrepresents Kant who argues that we should not "manipulate [others] to accomplish our own purposes." This is all Kant means by treating people as a means to an end. It is about moral virtue in ethics underlying our actions. So Kant would not take issue with these cases on their face. 
"...we will never be able to use other people as means to our end of getting a job"
  • As long as there is no exploitation of the person, Kant would not object to this. If you hypothetically manipulated someone to get you a job, Kant would simply argue against this. 
"...we will never be able to use other people as means to our end of having children"
  • If you manipulate your spouse or partner in a relationship just to have children Kant would see this as wrong. If you have respect for one another as rational beings, and mutually desire to have children and share this in honesty, Kant would be pleased with this. All Kant want is for us to act with moral virtue. 

Conclusion
  • This is straightforward. Pro did not even attempt to show a contradiction. The arguments seem to be "x part of Kant that I didn't understand and why this is bad," which doesn't show that Kant is inconsistent, and second, just misrepresents his arguments. 
Round 3
Pro
#5
I think I have to concede this debate. Regardless of how I worded my prompts, GPT-3 would repeat the same stupid argument it used in R2, or else instead end up arguing against the Pro position. I learned a lot from this debate about GPT-3, most importantly that it's not quite capable of intelligently representing both sides of a philosophical argument.

Thank you for accepting the debate.
Con
#6
  • Okay.