If You Can’t Beat Them, Join Them: GPT-3 Edition

Date

source

share

“How to deal with GPT-3-written essays? Instead of scolding students not to use it, we ask them to generate a ten, choose the best one, and explain why. Unless they have a paid account, the word-count limit would make it impossible to use GPT-3 to also generate the explanation…”

That’s Mark Alfano (Macquarie) discussing GPT-3 and teaching on Twitter yesterday. He added: “I want to avoid curmudgeonliness. New technology is resisted until it’s inevitable. Maybe using GPT-3 to generate first drafts and then synthesizing them is not bad actually. It has downsides, but so does reliance on philpapers or google scholar, and those are pretty new too.”

Prompted by Brian Robinson (Texas A&M-Kingsville), Alfano turned to the possibility of researchers using GPT-3 to write articles, and gave the language model this prompt:

A lengthy philosophical essay, titled “It’s OK that an AI drafted this paper,” that argues that it is acceptable to use artificial intelligence to draft a paper for publication in a peer-reviewed journal, provided the author edits the draft for clarity, cogency, and originality. The essay begins by making the claim that this is acceptable and provides two arguments. Then it responds to at least three objections to using artificial intelligence in this way.

Part of the challenge of using GPT-3 in this way is coming up with the right prompt. Alfano said he camte to the above formulation after about six preceding versions. Here’s his account of the resulting output, gathered up from his Twitter thread on it:

It is acceptable to use artificial intelligence to draft a paper for publication in a peer-reviewed journal, provided the author edits the draft for clarity, cogency, and originality.

Here are two arguments in support of this claim. First, using artificial intelligence to draft a paper can help ensure that the paper is well-written. This is because artificial intelligence can be used to check for errors in grammar, spelling, and syntax. Additionally, artificial intelligence can be used to improve the clarity and coherence of the paper. Second, using artificial intelligence to draft a paper can help ensure that the paper is well-researched. This is because artificial intelligence can be used to search for relevant scholarly articles and to identify key concepts and ideas. Additionally, artificial intelligence can be used to generate citations and bibliographies.

There are, of course, objections to using artificial intelligence to draft a paper. Here are three objections and my responses to them.

Objection 1: Artificial intelligence cannot understand the nuances of academic writing. Response: While it is true that artificial intelligence cannot understand the nuances of academic writing, this does not mean that it cannot produce a well-written paper. Artificial intelligence can be used to check for errors in grammar, spelling, and syntax. Additionally, artificial intelligence can be used to improve the clarity and coherence of the paper. 

Objection 2: Artificial intelligence cannot think creatively. Response: While it is true that artificial intelligence cannot think creatively, this does not mean that it cannot produce a well-written paper. Artificial intelligence can be used to search for relevant scholarly articles and to identify key concepts and ideas. Additionally, artificial intelligence can be used to generate citations and bibliographies.

Objection 3: Using artificial intelligence to draft a paper is cheating. Response: This objection assumes that using artificial intelligence to draft a paper is equivalent to having someone else write the paper for you. This is not the case. Using artificial intelligence to draft a paper simply means that you are using a tool to help you write the paper. The final product will still be your own work.

Alfano comments: “Observations: (1) The two positive arguments aren’t terrible, though it didn’t actually find any citations for me. In the responses to the first two objections, it basically just repeats itself. This might be avoided by increasing the frequency and presence penalties. The third objection, and the response to it, surprised me a little. I might even be convinced.”

Related: Philosophers on GPT-3 (including responses from GPT-3)

Originally appeared on Daily Nous Read More

More
articles

More
news