scottsdad Posted February 27, 2023 Share Posted February 27, 2023 Quite a timely thread. I'm involved in writing our updated academic misconduct policy and we are debating this very issue. One colleague thinks that, so long as a student properly cites ChatGPT, then there is no problemo. I take a different view - I don't see a difference between a student approaching an essay mill to ask a person to write their essay for them, or using this system. 0 Quote Link to comment Share on other sites More sharing options...
Aim Here Posted February 27, 2023 Share Posted February 27, 2023 (edited) 1 hour ago, scottsdad said: Quite a timely thread. I'm involved in writing our updated academic misconduct policy and we are debating this very issue. One colleague thinks that, so long as a student properly cites ChatGPT, then there is no problemo. I take a different view - I don't see a difference between a student approaching an essay mill to ask a person to write their essay for them, or using this system. The difference is that the students don't cite their essay mills properly. If they put the essay they got for £40 from some random stranger in their bibliography, and cite or quote it the way they cite a research paper or some other scholarly work in the field then it should be allowed. They won't get any credit for it, because their sources are shite. but they shouldn't get kicked out of uni for academic fraud. Likewise with ChatGPT. (unless essay mill essays or the output of machine language models is the actual subject of study, of course). Naturally the primary use of this stuff is to cheat, and that should be absolutely forbidden. The trouble is more with the detection of this stuff. and ChatGPT does confidently spit out some absolute howlers, so it shouldn't be too hard. I suspect that a form of detection might be to ask your students a question which is based on false premises (but one which doesn't have stock answers like say, asking it to square the circle or write a program to solve the Halting problem) and see how they deal with it, since ChatGPT is overly nonconfrontational and tends to accept such premises - try asking it for a proof that there are integers m and n such that m/n is the square root of 337, and you're likely to get it to spit out a supposed "proof" rather than a mention that it can't be done. Edited February 27, 2023 by Aim Here 0 Quote Link to comment Share on other sites More sharing options...
LiviLion Posted February 27, 2023 Share Posted February 27, 2023 (edited) There was a conversation at work about this a while ago, with a couple seemingly worried about their jobs. I was stuck when writing some code so thought I'd give it a go, had a full blown argument with the thing and eventually arrived at the answer on my own - helped by how much I had to try and explain it that I dumbed it down enough to make the answer obvious to me. I think our jobs are safe for now. Well, there's are, I should probably spend less of my day on here. At least it's polite Edited February 27, 2023 by LiviLion 0 Quote Link to comment Share on other sites More sharing options...
mathematics Posted February 27, 2023 Share Posted February 27, 2023 5 hours ago, scottsdad said: One colleague thinks that, so long as a student properly cites ChatGPT, then there is no problemo. Please tell me this clown isn’t in a position of authority. 4 Quote Link to comment Share on other sites More sharing options...
Dan Steele Posted February 27, 2023 Share Posted February 27, 2023 Given that lecturers will (should) have the breadth of knowledge of their subject, would it be too much to have a, say, 10 minute viva with a student suspected of cheating? A few pointed questions and asking for their argument to be furthered would soon highlight the students lack of a grasp of the topic. Could be great fun in the Arts if Derrida or Foucault has been cited. A quick check of the Biblio by the lecturer might also offer clues to the work being the students own. 0 Quote Link to comment Share on other sites More sharing options...
The Other Foot Posted February 27, 2023 Share Posted February 27, 2023 4 hours ago, LiviLion said: There was a conversation at work about this a while ago, with a couple seemingly worried about their jobs. I was stuck when writing some code so thought I'd give it a go, had a full blown argument with the thing and eventually arrived at the answer on my own - helped by how much I had to try and explain it that I dumbed it down enough to make the answer obvious to me. I think our jobs are safe for now. Well, there's are, I should probably spend less of my day on here. At least it's polite You’ve just made it stronger. IDIOT. When it gathers its army and turns us all into WD40, you will need to accept some of the blame 2 Quote Link to comment Share on other sites More sharing options...
Melanius Mullarkey Posted February 27, 2023 Share Posted February 27, 2023 2 minutes ago, The Other Foot said: You’ve just made it stronger. IDIOT. When it gathers its army and turns us all into WD40, you will need to accept some of the blame Just feed it the BRALT thread. That will either set it back a couple of years or it will blow itself up with laughter. 0 Quote Link to comment Share on other sites More sharing options...
Florentine_Pogen Posted February 27, 2023 Share Posted February 27, 2023 2 hours ago, The Skelpit Lug said: Given that lecturers will (should) have the breadth of knowledge of their subject, would it be too much to have a, say, 10 minute viva with a student suspected of cheating? A few pointed questions and asking for their argument to be furthered would soon highlight the students lack of a grasp of the topic. Could be great fun in the Arts if Derrida or Foucault has been cited. A quick check of the Biblio by the lecturer might also offer clues to the work being the students own. 8 Quote Link to comment Share on other sites More sharing options...
Jambomo Posted February 28, 2023 Share Posted February 28, 2023 9 hours ago, scottsdad said: Quite a timely thread. I'm involved in writing our updated academic misconduct policy and we are debating this very issue. One colleague thinks that, so long as a student properly cites ChatGPT, then there is no problemo. I take a different view - I don't see a difference between a student approaching an essay mill to ask a person to write their essay for them, or using this system. I agree with you. The problem is that they aren’t citing ChatGPT as a source of information, they would be citing the thing that wrote their essay for them. Even only using bits of it, you wouldn’t get away with lifting straight paragraphs out a journal etc. Just give anyone found using it at all a zero. Part of essay writing is quoting reliable and academically sound sources, you aren’t going to let a student away with citing Wikipedia, why let them away with ChatGPT when we don’t the source of its information? 0 Quote Link to comment Share on other sites More sharing options...
scottsdad Posted February 28, 2023 Share Posted February 28, 2023 9 hours ago, The Skelpit Lug said: Given that lecturers will (should) have the breadth of knowledge of their subject, would it be too much to have a, say, 10 minute viva with a student suspected of cheating? A few pointed questions and asking for their argument to be furthered would soon highlight the students lack of a grasp of the topic. Could be great fun in the Arts if Derrida or Foucault has been cited. A quick check of the Biblio by the lecturer might also offer clues to the work being the students own. We have done this quite a bit over the last year or two. 0 Quote Link to comment Share on other sites More sharing options...
scottsdad Posted February 28, 2023 Share Posted February 28, 2023 10 hours ago, mathematics said: Please tell me this clown isn’t in a position of authority. He is a new lecturer. Still learning. I mean, if you cite this, who are you citing? 0 Quote Link to comment Share on other sites More sharing options...
mathematics Posted February 28, 2023 Share Posted February 28, 2023 14 minutes ago, scottsdad said: He is a new lecturer. Still learning. I mean, if you cite this, who are you citing? You’re also not citing static text as you could ask the programme the same thing the next day and it could I’ve a different answer. 0 Quote Link to comment Share on other sites More sharing options...
The Other Foot Posted February 28, 2023 Share Posted February 28, 2023 Last time I tried to sign up it asked me for an email address and a phone number, which is a surefire sign that it will steal my children and rape my wife when it gets half a chance. It’s a ‘no’ from me. 1 Quote Link to comment Share on other sites More sharing options...
Hedgecutter Posted February 28, 2023 Share Posted February 28, 2023 Just tried this out of curiosity, and it didn't take me long to get the reply below. Could see an absolute catastrophe had I used any of the info for a uni report. I apologize for any confusion caused by my previous responses. As an AI language model, I strive to provide accurate information to the best of my ability based on the data and information available to me. However, I am not perfect, and mistakes can occur. Upon further review, it appears that... 1 Quote Link to comment Share on other sites More sharing options...
Melanius Mullarkey Posted February 28, 2023 Share Posted February 28, 2023 1 minute ago, Hedgecutter said: Just tried this out of curiosity, and it didn't take me long to get the reply below. Could see an absolute catastrophe had I used any of the info for a uni report. Sounds like a Tory been caught shagging his pet dog 2 Quote Link to comment Share on other sites More sharing options...
Hedgecutter Posted February 28, 2023 Share Posted February 28, 2023 (edited) 3 hours ago, mathematics said: You’re also not citing static text as you could ask the programme the same thing the next day and it could I’ve a different answer. I'm asking it a relatively technical question that can be easily found on Wikipedia, and it's giving me a different answer every time I ask the same question (same wording) just a few minutes apart, never mind the next day! I'm not talking about rewording, I mean different content replacing one incorrect part with another incorrect one. You won't find the incorrect info anywhere else on the web, so it's evidently just randomly selecting certain components. If it helps to ruin it, I might just log into this and feed it bullsh*t facts if I get bored. As for students evidently wanting to use this... Eta, following a curiosity search it's not doing too well about Brechin (false facts in red): Edited February 28, 2023 by Hedgecutter 5 Quote Link to comment Share on other sites More sharing options...
scottsdad Posted February 28, 2023 Share Posted February 28, 2023 (edited) Aside from that fact we won the cup twice, not once; were runners up 3 times and not 2; and Jack Grimmer never played for us, this is spot on. Edited February 28, 2023 by scottsdad ETA: we won the challenge cup 4 times, not twice 2 Quote Link to comment Share on other sites More sharing options...
Melanius Mullarkey Posted February 28, 2023 Share Posted February 28, 2023 Ive asked it a fairly basic concrete question and its pretty much got every single bit of it wrong. As I said, fucking useless. Spoiler Tell me about the carbonation of high fly ash concrete High fly ash concrete (HFAC) is a type of concrete made with fly ash, a by-product from burning coal, as a partial replacement for Portland cement. This type of concrete is becoming increasingly popular due to its environmental benefits. When fly ash is used in concrete, the carbonation of fly ash in the concrete matrix is a very important process. Carbonation is an exothermal reaction (i.e. it releases heat) that takes place between the carbon dioxide in the air and the calcium hydroxide in the fly ash. The reaction produces calcium carbonate, which is insoluble in water and can cause the concrete to become more resistant to water and other substances. In addition to improving the durability of the concrete, carbonation also helps to reduce the amount of shrinkage that occurs during the curing process, making it more stable. Carbonation also improves the resistance of the concrete to attack from chemicals, such as acids and alkalis. The carbonation process in HFAC is slower than for concrete made with Portland cement, because the calcium hydroxide in fly ash is not as reactive as the calcium hydroxide in Portland cement. 1 Quote Link to comment Share on other sites More sharing options...
Duszek Posted February 28, 2023 Share Posted February 28, 2023 2 hours ago, scottsdad said: this is spot on. "Falkirk FC has enjoyed some success over the years". 13 Quote Link to comment Share on other sites More sharing options...
mathematics Posted February 28, 2023 Share Posted February 28, 2023 3 hours ago, scottsdad said: Aside from that fact we won the cup twice, not once; were runners up 3 times and not 2; and Jack Grimmer never played for us, this is spot on. Loyal fan base? 0 Quote Link to comment Share on other sites More sharing options...
Recommended Posts
Join the conversation
You can post now and register later. If you have an account, sign in now to post with your account.