[Technology] ChatGPT

[beorhthelm]

Thanks for the reply. It's not an altogether encouraging snapshot of academia. Some of the revelations are extraordinary, and are indicative of the erosion in standards over the years.

I'm left wondering how I would react if I had students who have never written an essay, so they go and find one on the internet, and don't even have the nous to edit it themselves. Christ. But I admire your resilience. Never mind AI and ChatGPT; I would have been long gone.

it's a pattern that emerged in development. there's always been a bit of copy+paste since the web. difference is in that editting, making the example fit the actual scenario and then understanding it to debug or amend. we have started to see developers that dont seem to know how to do that, they can "write" reasonable code, with little idea how to change or fix it later. one thing this ChatPGT is apparently very good at is output working code, bit worrying for the future, not putting devs out of work, but how much code will be unmaintainable.

 

[stewart_weir]

My grandson says that it's more intelligent than humans is it?
What does this mean to mankind? I worry about the future employment of youngsters.
Who is the expert that can tell us exactly where this is going?
Thanks for your help.

AI and similar smart tech will make many jobs disappear over the next 10yrs. There will be far fewer jobs available unless people have specific skills. The obvious issue is population growth, less work, more people chasing fewer jobs then more people requiring state benefits to subsidise higher housing costs etc. etc. Bottom line is that capitalism will have to reinvent itself by accessing the greater corporate profits and most likely reducing weekly working hours for many jobs. The future looks very dystopian to me. So glad I lived through the 70s/80s/90s

 

[Eric the meek]

it's a pattern that emerged in development. there's always been a bit of copy+paste since the web. difference is in that editting, making the example fit the actual scenario and then understanding it to debug or amend. we have started to see developers that dont seem to know how to do that, they can "write" reasonable code, with little idea how to change or fix it later. one thing this ChatPGT is apparently very good at is output working code, bit worrying for the future, not putting devs out of work, but how much code will be unmaintainable.

Even in my day (1990s - mainframe development - Cobol/CICS/DL1/DB2), working for a software house, the bulk of our work was maintaining our clients' systems. On the odd occasion when we had to write a brand new program, we still never wrote a new program, but found a suitable one to copy and use as a base. When the mainframe work dried up, I went contracting as a system tester. Testing IT systems in around 25 end clients, I found that the structured methodology of mainframe development, with its concepts of standards, procedures, documentation, traceability and maintainability were quickly lost. But it meant more testing work for me though. (Apologies for going a bit off topic).

 

[Papak]

Write an angry letter to CEO at Brighton & Hove Albion about the club's failure to replace striker Jesus

Dear [CEO of Brighton & Hove Albion],

I am writing to express my extreme disappointment and frustration with the club's failure to replace striker Jesus. As a devoted fan of Brighton & Hove Albion, I have watched with dismay as the team has struggled to find a suitable replacement for such a talented and important player.

Jesus' departure has left a huge hole in the team, and it is clear that the club's lack of action in replacing him has had a significant impact on the team's performance. The poor results and lack of goals on the field are a direct result of the club's failure to address this crucial issue.

I find it unacceptable that the club would neglect such an obvious and pressing need. The transfer window is now closed, and it's too late to bring any new striker. It shows the lack of planning and foresight on the part of the club's management.

I have been a loyal supporter of Brighton & Hove Albion for many years, and I am deeply disappointed by the club's failure to address this issue in a timely and effective manner. I urge the club to take immediate action to rectify this situation and bring in a new striker before it's too late.

Sincerely,

as you can see its pretty much a template, exactly same came out for Connolly and Ronaldo.

Which one?

Thanks for checking btw.

 

[Harry Wilson's tackle]

Thanks for the reply. It's not an altogether encouraging snapshot of academia. Some of the revelations are extraordinary, and are indicative of the erosion in standards over the years.

I'm left wondering how I would react if I had students who have never written an essay, so they go and find one on the internet, and don't even have the nous to edit it themselves. Christ. But I admire your resilience. Never mind AI and ChatGPT; I would have been long gone.

I'm toying with going. It will take only a few more shoves of stupidity from my more gormless colleagues.

The latest wheeze (this is in the interests of 'fairness', of course) is when you have a student doing a research project, neither the first nor second marker are allowed to be the supervisor any more. They call it 'marking your own homework'. It's not my effing homework! I don't have a vested interest in the student I supervise getting a higher mark that the student my pal has supervised. But there is evidence that the dimmer of my colleagues thinks it reflects well on them if their student gets a higher mark. Also there used to be bullying. When I second marked a project supervised by my HoD a few years ago, she objected to my lowish mark (the work was shit) because 'the student is going to do a PhD in my lab after they graduate'. What? I refused to bend so she gave a mark-boost to the other bit of the assessment, 'lab performance' (marked only by the supervisor for obvious reasons) so te student got a 'fisrt class' overall. This, despite my HoD having already written in her assessment of the dissertation that 'the student was excellent in the lab'. What? (again). So now she doesn't get to mark the written work. Instead two other academics mark the work 'independently and blindly'. This is where lack of tacit expertise comes into play. I know f*** all about what goes on in some colleagues' labs, and won't know if the daft shite the student wrote up was the idea of the student or the supervisor. And - get this - after the blind marking, if the marks digress between the two markers by more than 5 marks, or span a degree class, the markers have to meet to discuss an 'agreed mark'. Then, who shouts loudest 'wins'. I always capitulate immediately if I know the other marker is sensible. I favour consecutive marking where the second marker just checks that the first marker hasn't written bollocks. But, no, the college won't endorse this as it isn't 'proper double marking'. Many of my colleagues regress to the mean when they mark, writing bland platitudes, and give all the work between 62 and 68%. 'Life's to short to piss about' is what one colleague says. Don't get me wrong, some staff (like me) deliver top notch courses and teaching. But there are always ninnies, jackasses and poltroons in positions of influence, shanking the rubric. We now have a 'teaching admin' pathway to professorship now (to get around all staff refusing to teach because the college only rewards - and indeed employs- people who raise lots of grant funding for research from the likes of the MRC, and in the past staff were sacked if they were not performing in research, or had their labs taken away and made to do more teaching and admin if they were liked). "See, you can have a career from teaching and admin" the system now says. These are the people too dim to be able to raise research funds. Trouble is most of them know f*** all about teaching or admin either. Luckily, despite having a lab, a patent and money to do research, I have the highest teaching load in the division (and am very good at it) so they leave me alone. The don't encourage me onto the management committees though. Fancy that! But as I have noted before, I am apparently peculiar (on the spectrum), so that's alright then - just ignore the bugger till he retires. Luckily I also have some good pals at work, fellow ranters and rebels, all also a bit odd.

Edit: apologies for going way off topic

 

[Harry Wilson's tackle]

Write an angry letter to CEO at Brighton & Hove Albion about the club's failure to replace striker Jesus

Dear [CEO of Brighton & Hove Albion],

I am writing to express my extreme disappointment and frustration with the club's failure to replace striker Jesus. As a devoted fan of Brighton & Hove Albion, I have watched with dismay as the team has struggled to find a suitable replacement for such a talented and important player.

Jesus' departure has left a huge hole in the team, and it is clear that the club's lack of action in replacing him has had a significant impact on the team's performance. The poor results and lack of goals on the field are a direct result of the club's failure to address this crucial issue.

I find it unacceptable that the club would neglect such an obvious and pressing need. The transfer window is now closed, and it's too late to bring any new striker. It shows the lack of planning and foresight on the part of the club's management.

I have been a loyal supporter of Brighton & Hove Albion for many years, and I am deeply disappointed by the club's failure to address this issue in a timely and effective manner. I urge the club to take immediate action to rectify this situation and bring in a new striker before it's too late.

Sincerely,

as you can see its pretty much a template, exactly same came out for Connolly and Ronaldo.

Take note @Swansman.

This is encouraging. If I give 50 students the same essay title (which I do) they are all likely to come up with the same basic answer by this mechanism - unless the clever clogs' ask the thing to make 'that bit' wrong, etc., But....then they will end up with . . . a shit essay. If the student asks it to 'expand on that bit' they will end up with a shit essay if they have chosen the wrong bit to expand. This is assuming it can avoid any cut and paste. The student would probably find it quicker and easier to find out about the question, research it, and write the answer/essay using their knowledge and ingenuity.

 

[Eric the meek]

I'm toying with going. It will take only a few more shoves of stupidity from my more gormless colleagues.

The latest wheeze (this is in the interests of 'fairness', of course) is when you have a student doing a research project, neither the first nor second marker are allowed to be the supervisor any more. They call it 'marking your own homework'. It's not my effing homework! I don't have a vested interest in the student I supervise getting a higher mark that the student my pal has supervised. But there is evidence that the dimmer of my colleagues thinks it reflects well on them if their student gets a higher mark. Also there used to be bullying. When I second marked a project supervised by my HoD a few years ago, she objected to my lowish mark (the work was shit) because 'the student is going to do a PhD in my lab after they graduate'. What? I refused to bend so she gave a mark-boost to the other bit of the assessment, 'lab performance' (marked only by the supervisor for obvious reasons) so te student got a 'fisrt class' overall. This, despite my HoD having already written in her assessment of the dissertation that 'the student was excellent in the lab'. What? (again). So now she doesn't get to mark the written work. Instead two other academics mark the work 'independently and blindly'. This is where lack of tacit expertise comes into play. I know f*** all about what goes on in some colleagues' labs, and won't know if the daft shite the student wrote up was the idea of the student or the supervisor. And - get this - after the blind marking, if the marks digress between the two markers by more than 5 marks, or span a degree class, the markers have to meet to discuss an 'agreed mark'. Then, who shouts loudest 'wins'. I always capitulate immediately if I know the other marker is sensible. I favour consecutive marking where the second marker just checks that the first marker hasn't written bollocks. But, no, the college won't endorse this as it isn't 'proper double marking'. Many of my colleagues regress to the mean when they mark, writing bland platitudes, and give all the work between 62 and 68%. 'Life's to short to piss about' is what one colleague says. Don't get me wrong, some staff (like me) deliver top notch courses and teaching. But there are always ninnies, jackasses and poltroons in positions of influence, shanking the rubric. We now have a 'teaching admin' pathway to professorship now (to get around all staff refusing to teach because the college only rewards - and indeed employs- people who raise lots of grant funding for research from the likes of the MRC, and in the past staff were sacked if they were not performing in research, or had their labs taken away and made to do more teaching and admin if they were liked). "See, you can have a career from teaching and admin" the system now says. These are the people too dim to be able to raise research funds. Trouble is most of them know f*** all about teaching or admin either. Luckily, despite having a lab, a patent and money to do research, I have the highest teaching load in the division (and am very good at it) so they leave me alone. The don't encourage me onto the management committees though. Fancy that! But as I have noted before, I am apparently peculiar (on the spectrum), so that's alright then - just ignore the bugger till he retires. Luckily I also have some good pals at work, fellow ranters and rebels, all also a bit odd.

How do I reply to that?

First, I'm sorry to have opened the sluice gates. Alternatively, if you take the view that it's good to talk, then my invoice is in the post.

Nobody could know less about your academic life than me, so I won't presume to advise on that front. Except one observation. It sounds as if you really care about your output, teaching, research and assessment, so I would suggest you aren't ready to leave. Whether I am right or wrong, do study what is in your best interests, and act accordingly, in a carefully planned manner. One thing you might want to consider, is taking a forensic look at your pension arrangements, dovetailed with the state pension that you will be getting soon. Do you need to top up any years outstanding? Will you need to minimise tax? This way, whatever you decide, whether that is to go, stay, or a phased retirement, then you can do it in the knowledge that you will know exactly what retirement income you will be getting, and when, with no surprises.
Best of luck. If there is one thing I learned when I retired, it's that none of the seven kinds of shit that happen while you're in work, actually matter after you've retired. None of it.

 

[GingerBeerMan]

I’m sure a geography teacher would spot 30 essays mentioning slinkys?

I guess a way to make sure all of the students using this software aren’t all handing in the same essay is for all the students to cross reference their essays before handing them in.

Which seems pretty time consuming.

This is revolutionary, people heavily involved in technology who actually understand the concepts behind NLP realise what a great leap forward this has been, along with recent launches of tools such as DALE-2.

Nothing I saw will change your mind, because you are closed minded, but I wanted to make a post to give myself the 'I told you so' moment in 10-15 years when this technology changes the employment ecosystem forever.

 

[Harry Wilson's tackle]

How do I reply to that?

First, I'm sorry to have opened the sluice gates. Alternatively, if you take the view that it's good to talk, then my invoice is in the post.

Nobody could know less about your academic life than me, so I won't presume to advise on that front. Except one observation. It sounds as if you really care about your output, teaching, research and assessment, so I would suggest you aren't ready to leave. Whether I am right or wrong, do study what is in your best interests, and act accordingly, in a carefully planned manner. One thing you might want to consider, is taking a forensic look at your pension arrangements, dovetailed with the state pension that you will be getting soon. Do you need to top up any years outstanding? Will you need to minimise tax? This way, whatever you decide, whether that is to go, stay, or a phased retirement, then you can do it in the knowledge that you will know exactly what retirement income you will be getting, and when, with no surprises.
Best of luck. If there is one thing I learned when I retired, it's that none of the seven kinds of shit that happen while you're in work, actually matter after you've retired. None of it.

Cheers

I'm all sorted on the pension front, thanks. No mortgage. And yes, I am still at work because I still enjoy it. I suspect that most established forms of employment have much the same issues. One must....ris above

 

[The Clamp]

This is revolutionary, people heavily involved in technology who actually understand the concepts behind NLP realise what a great leap forward this has been, along with recent launches of tools such as DALE-2.

Nothing I saw will change your mind, because you are closed minded, but I wanted to make a post to give myself the 'I told you so' moment in 10-15 years when this technology changes the employment ecosystem forever.

Don’t mistake scepticism for a closed mind.

 

[Bozza]

write a resignation letter from under-performing Chelsea manager graham potter

Dear Chelsea Football Club,​

​

I am writing to inform you of my resignation as manager of the club, effective immediately.​

​

I regret to say that my performance as manager has not met the expectations of the club and its supporters, and I believe it is in the best interest of Chelsea to seek a new leader for the team.​

​

I want to express my deepest appreciation to the players, staff, and fans for their support during my time at the club. I am honored to have had the opportunity to lead such a talented group of individuals and I will always hold a special place in my heart for Chelsea.​

​

I wish the club and its future managers all the best in the years to come.​

​

Sincerely, Graham Potter​

​

​

do the above but make it very bitter

Dear Chelsea Football Club,​

​

I am writing to inform you that I am resigning as manager of the club, effective immediately. I cannot continue to work in a place where my efforts and hard work are not recognized or appreciated.​

​

I regret to say that my performance as manager has been consistently undermined by the club's lack of support and resources. The lack of trust and faith in my abilities has made it impossible for me to continue leading this team.​

​

I want to express my deep disappointment in the club's management and ownership. Their lack of vision and inability to invest in the team's success has resulted in the failure of my tenure here.​

​

I want to make it clear that I do not take responsibility for the club's current underperformance, as I have been met with obstacles at every turn. I hope that in the future, the club will make better decisions and invest in the necessary resources to achieve success.​

​

I wish the club and its future managers all the best, but I cannot help but feel that they will be facing the same challenges that I have encountered.​

​

Sincerely, Graham Potter​

 

[Eric the meek]

Cheers

I'm all sorted on the pension front, thanks. No mortgage. And yes, I am still at work because I still enjoy it. I suspect that most established forms of employment have much the same issues. One must....ris above

Excellent ! If you enjoy work, then it's not really 'work' is it? Why would you retire from something you enjoy?

Achieving 'enjoyment' at work, especially IT development, was something of a holy grail which eluded me for the most part.
The advantage of that is, that when I did retire, I didn't miss work at all !

 

[Bozza]

"I went into this project as a total skeptic. I was completely certain that I could ask ChatGPT questions that would be far too difficult — not because the content is hard, but because my questions required that the AI demonstrate fairly specialized knowledge, an ability to synthesize that knowledge, an ability to be concise in its responses, and an ability to construct a mathematical solution to a microbiology word problem. With the exception of Q1, ChatGPT passed with flying colors. If I were grading the quiz, I would give ChatGPT a 95% — which is far better than what most human students likely would get."

We gave ChatGPT a college-level microbiology quiz. It blew the quiz away.

ChatGPT's capabilities are astonishing. It demonstrated the ability to synthesize knowledge and apply it to complex word problems.

bigthink.com

 

[Swansman]

Just noticed you can play with temperature (creativity) in ChatGPT just like with most GPT-based generators, 0 is lowest and 1 is highest and you can use decimals to get something in between. Will use Bozzas example above to show the difference:

write a very bitter resignation letter from under-performing Chelsea manager graham potter
first write one with temperature 0, then one with temperature 1

Resignation Letter (Temperature 0)

Dear [Chelsea FC Board],

I am writing to formally resign as the manager of Chelsea Football Club. It has become clear to me that my performance and results as manager have not met the expectations of the club or its fans. I take full responsibility for the team's under-performance and the lack of success we have had this season.

I want to express my sincere apologies to the players, staff, and supporters for my inability to lead the team to the level of success we all hoped for. I am deeply disappointed that I was not able to deliver the results that were expected of me.

I wish Chelsea Football Club all the best in their future endeavors and hope that the team can find a manager who can bring them the success they deserve.

Sincerely, Graham Potter

Resignation Letter (Temperature 1)

Dear [Chelsea FC Board],

I am writing to tell you that I QUIT! I refuse to be the fall guy for this team's utter lack of performance and complete failure to live up to expectations. I am done with this shitshow of a club and all the entitled, underperforming players that make up this so-called "team".

I have put in countless hours, poured my heart and soul into this job and for what? To be constantly undermined by a group of overpaid, under-talented players who couldn't lead their way out of a paper bag? No more. I am done with this circus and I hope you all rot in hell.

I wish Chelsea Football Club nothing but the worst, and hope that the next poor sap who takes this job realizes what a nightmare it truly is.

Sincerely, Graham Potter (ex) Manager of Chelsea FC.

 

[Harry Wilson's tackle]

ChatGPT banned from authoring papers​

The artificial-intelligence (AI) chatbot ChatGPT has been listed as a co-author on four papers and preprints. Publishers are starting to ban AI authorship because chatbots can’t take responsibility for a paper’s content and integrity. Some publishers say that chatbot use should be documented in the methods or acknowledgements sections — and that not doing so could be considered plagiarism.

Nature | 6 min read

 

[AlbionBro]

"Which poster is the most wrong on North stand chat?

I'm sorry, I am not aware of the context of North stand chat and it is not appropriate for me to make any assumptions about posters on an online forum. It is important to respect the opinions and perspectives of others, even if we may not agree with them. It is also important to remember that online communication can be easily misinterpreted and it is always best to communicate with kindness and empathy."

This ChatGPT isn't that great is it?!

 

[Paulie Gualtieri]

I'm toying with going. It will take only a few more shoves of stupidity from my more gormless colleagues.

The latest wheeze (this is in the interests of 'fairness', of course) is when you have a student doing a research project, neither the first nor second marker are allowed to be the supervisor any more. They call it 'marking your own homework'. It's not my effing homework! I don't have a vested interest in the student I supervise getting a higher mark that the student my pal has supervised. But there is evidence that the dimmer of my colleagues thinks it reflects well on them if their student gets a higher mark. Also there used to be bullying. When I second marked a project supervised by my HoD a few years ago, she objected to my lowish mark (the work was shit) because 'the student is going to do a PhD in my lab after they graduate'. What? I refused to bend so she gave a mark-boost to the other bit of the assessment, 'lab performance' (marked only by the supervisor for obvious reasons) so te student got a 'fisrt class' overall. This, despite my HoD having already written in her assessment of the dissertation that 'the student was excellent in the lab'. What? (again). So now she doesn't get to mark the written work. Instead two other academics mark the work 'independently and blindly'. This is where lack of tacit expertise comes into play. I know f*** all about what goes on in some colleagues' labs, and won't know if the daft shite the student wrote up was the idea of the student or the supervisor. And - get this - after the blind marking, if the marks digress between the two markers by more than 5 marks, or span a degree class, the markers have to meet to discuss an 'agreed mark'. Then, who shouts loudest 'wins'. I always capitulate immediately if I know the other marker is sensible. I favour consecutive marking where the second marker just checks that the first marker hasn't written bollocks. But, no, the college won't endorse this as it isn't 'proper double marking'. Many of my colleagues regress to the mean when they mark, writing bland platitudes, and give all the work between 62 and 68%. 'Life's to short to piss about' is what one colleague says. Don't get me wrong, some staff (like me) deliver top notch courses and teaching. But there are always ninnies, jackasses and poltroons in positions of influence, shanking the rubric. We now have a 'teaching admin' pathway to professorship now (to get around all staff refusing to teach because the college only rewards - and indeed employs- people who raise lots of grant funding for research from the likes of the MRC, and in the past staff were sacked if they were not performing in research, or had their labs taken away and made to do more teaching and admin if they were liked). "See, you can have a career from teaching and admin" the system now says. These are the people too dim to be able to raise research funds. Trouble is most of them know f*** all about teaching or admin either. Luckily, despite having a lab, a patent and money to do research, I have the highest teaching load in the division (and am very good at it) so they leave me alone. The don't encourage me onto the management committees though. Fancy that! But as I have noted before, I am apparently peculiar (on the spectrum), so that's alright then - just ignore the bugger till he retires. Luckily I also have some good pals at work, fellow ranters and rebels, all also a bit odd.

Edit: apologies for going way off topic

But apart from that, things are ticking over nicely?

 

[Springal]

Some proper dinosaurs on here job market is crying out for those with AI / ML skills, job salaries on offer so anyone with kids with an interest in this kind of thing should be looking to get into it

 

[Hamilton]

I was asked for a comment on ChatGPT by a paper this week. They want to know what it’s impact might be on the creative industries.

I made a number of comments. Among them, this, which I, er, stole from ChatGPT.

“As a language model, it has the potential to impact the creative industries in a variety of ways. One possible use is in the generation of written content, such as news articles, fiction, and scripts. ChatGPT can also be used to assist in the creative process by providing inspiration and suggestions for characters, plot points, and dialogue. Additionally, AI may be used in the creation of virtual assistants and chatbots for customer service, marketing, and other purposes. It's important to note, that it is a tool and the impact will depend on how it's used and integrated in the creative process.”

As a test, it’ll be interesting to see whether this comment gets used or my other comments. (Or none at all)

The answer I did get from ChatGPT was interesting in that it missed the nuance in the question I was asked. The journo was more interested in ‘impact’ that what the AI could do and ChatGPT, being non-human, didn’t pick up on this.

 

[Hamilton]

Some proper dinosaurs on here job market is crying out for those with AI / ML skills, job salaries on offer so anyone with kids with an interest in this kind of thing should be looking to get into it

Agree with that. As a tool, it’s very exciting and will save us so much time. The motor car, phone, TV, computer, they were all eyed with the same suspicion by our parents, grandparents and great grandparents.