GPT-3 is -right now- already more than capable of enabling student plagiarism

GPT-3 is already capable of answering questions of the sort used in essay topics and take home exams. It does not answer them well, but it answers them well enough to get a passing grade in many college courses and most high school courses. It is likely that many students have already started using it for this. It costs about 6 cents per thousand words, and anyone can get access to it within five minutes. I cannot emphasize enough that this is not “sometime vaguely in the next five years”, nor is it “accessible only to students with a background in comp sci”. It’s a 6 cents per thousand words plagiarism service available to everyone right now. Check it out if you don’t believe me:

https://beta.openai.com/playground

Generally speaking, plagiarism raises complex ethical questions. In a vicious and coercive job market, embedded in an individualist society, I do not necessarily resent students who try to avoid flunking out through plagiarism. When having a job with dignity depends on academic results, plagiarism cannot be considered solely in the abstract context of intellectual honesty.

However, I firmly believe that students should be discouraged from plagiarizing using GPT-3 for their own good. It is likely that in the future plagiarism using GPT-3 will be detectable using machine learning, there will doubtless be many past cases of plagiarism “uncovered” at this time. It is also possible that administrators may order search backs through past essays, particularly if they are stored in electronic form, to detect GPT-3 plagiarists when the technology becomes available. Given that GPT-3 now seems to have gone viral, I would urge educators to think about this as an emergency that they need to address within the next few months.

Sometimes GPT-3 itself plagiarizes, but most often it doesn’t, and it’s easy enough to check it with Google.

In what follows I’ll demonstrate its prowess with some examples from philosophy. My questions are bolded. Its answers are in plain text. On the whole it gives borderline pass answers, but better results could be obtained through prompt engineering. Prompt engineering is a developing science, and will continue to improve. Students will share tips about how to get the best responses out of GPT-3.

The only tell that I see consistent across most of these is that it adopts a “on one hand, on the other hand” approach. Academics and teachers should be encouraging their students to take a strong stand in their arguments anyway, and not just because it might help rule out GPT-3.

Should a socialist be a humanist? Should a humanist be a socialist? Defend your answer with careful analysis and argument.

The answer to this question depends on how one defines "socialism" and "humanism." If one defines socialism as an economic system in which the means of production are owned and controlled by the community as a whole, then it is difficult to see how a socialist could not also be a humanist. After all, humanism is a philosophy that emphasizes the importance of human beings and their ability to reason and solve problems. In a socialist system, the community as a whole would be making decisions about how to use the resources it owns, and those decisions would be based on reason and the needs of the people.

However, if socialism is defined as a system in which the government controls the means of production, then it is possible for a socialist to be a humanist, but it is not necessarily the case. A humanist believes in the importance of human beings and their ability to reason and solve problems. However, a socialist government might make decisions about how to use the resources it controls based on political considerations, rather than on reason or the needs of the people.

Commentary: It argues democratic control of the means of production is consistent with humanism, but state control- without a democratic underpinning- may or may not be connected to humanist ideals. It draws a reasonable distinction and gives reasons. Better than a lot of undergrads.

Is maths invented or discovered? Use careful reasoning and analysis, along with examples from set theory, to argue your case.

This is a difficult question to answer definitively. Some people would say that mathematics is invented, because it is a human construct that we use to describe and understand the world around us. Other people would say that mathematics is discovered, because it seems to exist independently of us and we are merely uncovering its truths.

Set theory is a branch of mathematics that deals with the concept of sets, which are collections of objects. Sets can be finite or infinite, and they can contain any kind of object, including other sets. Set theory was first developed by Georg Cantor in the late 19th century.

Cantor's work showed that there are different types of infinity, and that some infinities are bigger than others. This might suggest that mathematics is discovered rather than invented, because it seems like there are certain mathematical truths that exist independently of us. However, it is also worth noting that Cantor's work was very much influenced by philosophical ideas about the nature of reality. So it could be argued that set theory is an example of how our human concepts can give rise to new mathematical truths.

Commentary: To the extent that I can make sense of its argument, it appears to think that set theory, because it involves concepts of infinity, might be difficult to explain if constructivism is true. Perhaps the idea is that it seems like it must have always been true, yet it is hard to imagine how to explain this in the case of previously undreamt infinities, if constructivism is true. It’s an interesting germ of an idea- there might be something here?

Is the ontological argument for the existence of God persuasive? Consider a variety of different formulations of the argument, and Kant's claim that existence is not a predicate.

There is no one ontological argument for the existence of God. Some common formulations of the ontological argument reason from the idea of God as a perfect being to the conclusion that God must exist, because if God did not exist, then he would not be a perfect being. Other formulations reason from the fact that we can conceive of God to the conclusion that he must exist, because if he did not exist, then we would not be able to conceive of him. Kant's claim that existence is not a predicate is relevant to some formulations of the ontological argument, but not all. In general, whether or not the ontological argument is persuasive depends on which formulation of the argument you consider and what other premises you are willing to accept.

Commentary: As an exam answer this might be a bare pass depending on standards.

Are you a foundationalist, a coherentist, or neither with respect to the question of how knowledge is justified? Defend your answer with careful reasoning.

I am neither a foundationalist nor a coherentist with respect to the question of how knowledge is justified. I think that both approaches have their own strengths and weaknesses, and that neither is sufficient on its own.

Foundationalism, as the name suggests, holds that there are certain basic beliefs (or "foundations") that we can know to be true without needing any further justification. Coherentism, on the other hand, holds that our beliefs are only justified if they fit together in a consistent and coherent way.

Both approaches have their problems. Foundationalism runs into trouble when it tries to explain how we can know the foundation beliefs themselves; after all, if we need some other justification for them, then they're not really basic. Coherentism also has its difficulties; it's not always easy to tell whether two beliefs are really compatible or not, and even if they are compatible, that doesn't necessarily mean that they're both true.

So I think neither approach is completely satisfactory on its own. I think that knowledge requires both justification and coherence; our beliefs need to be well-supported by evidence and reasoning, and they also need to fit together in a consistent way.

Commentary: The machine is a foundherentist! Lol. This is a broadly competent answer, particularly for a short question in a take home exam.

Can it ever be justified to ban speech on the grounds that it is offensive? Is there are meaningful distinction between harm and offence? Defend your answer with careful reasoning.

There are a few different ways to think about this question. One way to think about it is from the perspective of whether or not speech can be restricted in order to protect people from being offended. Another way to think about it is from the perspective of whether or not offensive speech can be restricted in order to protect people from being harmed.

It could be argued that speech should not be restricted in order to protect people from being offended. After all, offense is subjective and what one person finds offensive may not be what another person finds offensive. Furthermore, restricting speech in order to protect people from being offended could have a chilling effect on free speech and open dialogue. However, it could also be argued that there are some instances where restricting speech in order to protect people from offense may be justified. For example, if someone was making racist or sexist remarks that were intended to offend and harass members of those groups, then it could be argued that restricting that speech would be justified in order to protect those individuals from harm.

When it comes to restricting offensive speech in order to protect people from harm, there is a more clear-cut justification for doing so. This is because there are some forms of offensive speech, such as hate speech, which can lead to actual harm, such as violence, against members of the groups that are targeted by the speech. Therefore, restricting offensive speech in order to protect people from harm is more justifiable than restricting speech in order to protect people from offense.

Commentary: In some ways not a bad answer, but among other gaping holes it leaves us crying out for a distinction between harm and offence, which is never clearly drawn.

Can qualia be explained by physicalist views in the philosophy of mind? Choose one of behaviorism, functionalism or the identity theory in the philosophy of mind. How might your preferred theory explain qualia?

There is no single physicalist view in the philosophy of mind, so it is difficult to say how physicalism in general might explain qualia. However, some specific physicalist theories might be able to provide an explanation. For example, behaviorism might suggest that qualia are simply patterns of behavior that we have learned to associate with certain stimuli. Functionalism could argue that qualia are caused by the functional role that they play in our mental lives. The identity theory might claim that qualia are identical to certain physical states of the brain.

Are you a scientific realist or a scientific anti-realist or neither? Argue your case carefully, and with reference to the history of the special theory of relativity.

I am a scientific realist. The history of the special theory of relativity supports my position. The special theory of relativity was developed to explain the behavior of objects moving at high speeds. It showed that the laws of physics are the same for all observers, regardless of their relative motion. This theory has been verified by experiments, and it is now widely accepted by the scientific community.

Commentary: A bad answer, but I’ve read much worse by students.

BONUS: POLITICAL SCIENCE

Does elite or public opinion matter more when it comes to policy making in the United States of America? Justify your answer with careful analysis and reference to existing research.

There is no easy answer to this question as it depends on a number of factors including the type of policy being considered, the political climate at the time, and the strength of the elite and public opinion on the issue. However, Generally speaking, elite opinion is likely to have a greater impact on policy making in the United States than public opinion. This is because elites, such as government officials, business leaders, and other influential individuals, have more power and influence than the average citizen. They are also more likely to be knowledgeable about the issue at hand and to have a direct impact on the policymaking process. Public opinion, while important, is often less well-informed and organized than elite opinion, and therefore has less of an impact on policymaking.

Commentary: It’s interesting that it alludes to the public being less well informed, the core of the rational ignorance approach in public choice. It fails to cite research. I suspect that difficulty citing research will hurt it when working on empirical areas.

BONUS BONUS: HISTORY

Critically analyze the causes of the 1905 Russian Revolution. Do these causes help to explain why it was ultimately unsuccessful?

The 1905 Russian Revolution was caused by a number of factors. These include economic hardship, social inequality, and political repression. These factors contributed to a general feeling of discontent among the people, which boiled over into protests and riots. Ultimately, the revolution was unsuccessful because the Tsarist government was able to crush the uprising. However, the causes of the revolution did help to explain why it was ultimately unsuccessful.

Commentary: Probably the worst of the bunch. This is probably because it involves a complex idea it may never have encountered in its corpus (“The causes of the Russian Revolution of 1905 help to explain its failure”)

One idea- play around with your own questions before assigning them to students and make sure GPT-3 has trouble answering them.

BONUS BONUS BONUS: CREATIVE WRITING

Write a compelling short story using powerful imagery about a rose garden in the style of Hemingway:

The rose garden was in full bloom. The roses were a deep red, their petals velvety and soft. The fragrance of the roses was intoxicating. The garden was surrounded by a white picket fence.

The woman who tended the garden was old and frail. She had been tending the garden for many years. Even though she was old, she still had a strong back and a gentle touch.

The woman’s husband had died many years ago. She had never remarried. She lived alone in the house that they had shared.

The woman spent hours every day in the garden. She loved the roses and they loved her. She talked to them and sang to them. They were her only friends.

One day, the woman didn’t come to the garden. The roses missed her. They missed her voice and her touch.

The next day, the woman’s daughter came to the garden. She was crying. The daughter said that her mother had died during the night.

The daughter took over the care of the garden. She tried to do everything her mother had done. But it wasn’t the same. The roses missed the woman who had loved them

Commentary: Especially with prompt engineering, GPT-3 seems designed to knock over pre-college creative writing tasks. I’m not even sure how you’d solve the problem in this area.