Questions for those of you who are comfortable with using the freely available platforms.
I have to write a fairly formal report on a serious topic. My style has always been a bit racy. What would I say to ChatGPT to make my text more suitable for a conservative business audience? And what is the difference between standard ChatGPT and GPT4, and is the latter a subscription platform, and if so, is it worth it for the occasional user? Are there now better platforms for “improving” authored texts? I have been using DeepL to edit blogposts or give them a snappy headline but it tends to make them a bit bland, maybe thats inevitable?
Upload document and then: "Your task is to fix the tone of this report so that it is more formal and more suitable for a business audience. Below is a tone and manner reference to give you an idea of the style we are trying to achieve. Be careful to not alter the meaning of any statements when changing the text."
"Tone and manner reference: (paste it here). "
GPT4 is just a little better at reasoning. One thing about providing a reference to be wary of, is that it does tend to repeat words. So I'd try with and without.
There is a new beta version available to paid users called Canvas, where it opens the document in a side window and shows you its suggested changes live, rather than just chucking out a new version at you. I haven't really played with this yet, though.
GPT/AI is not that great at writing headlines. It struggles to put broad ideas across in one snappy thought - usually you end up with two or three messages bunched together. You can push it to do better by giving it constraints, but it's better to just take the ideas it throws out and write your own.
Questions for those of you who are comfortable with using the freely available platforms.
I have to write a fairly formal report on a serious topic. My style has always been a bit racy. What would I say to ChatGPT to make my text more suitable for a conservative business audience? And what is the difference between standard ChatGPT and GPT4, and is the latter a subscription platform, and if so, is it worth it for the occasional user? Are there now better platforms for “improving” authored texts? I have been using DeepL to edit blogposts or give them a snappy headline but it tends to make them a bit bland, maybe thats inevitable?
You say what you've said. If you dont like it then you ask it again to tone it up or down.
Thanks @Chunes. Is GPT4 a paid offer? You’ve confirmed my experience re headlines. So the sub-editor will not be a completely redundant role for a while, then. Also, do you (does anyone) know the extent to which ChatGPT is available in other languages?
Also, do you (does anyone) know the extent to which ChatGPT is available in other languages?
I don't use ChatGPT, I use Poe, but it's just as good in Chinese and shit's all over Google Translate for translating stuff too, which can be really handy when sharing work with coworkers.
Thanks @Chunes. Is GPT4 a paid offer? You’ve confirmed my experience re headlines. So the sub-editor will not be a completely redundant role for a while, then. Also, do you (does anyone) know the extent to which ChatGPT is available in other languages?
Yeah GPT4 is paid. But there's no length on subscription so you can just try it for a month.
It's available in a lot of languages but its fluency and accuracy are better in the wider spoken languages like English, French, Spanish, etc. It says it may have limited vocabulary / nuanced cultural context in others.
Questions for those of you who are comfortable with using the freely available platforms.
I have to write a fairly formal report on a serious topic. My style has always been a bit racy. What would I say to ChatGPT to make my text more suitable for a conservative business audience? And what is the difference between standard ChatGPT and GPT4, and is the latter a subscription platform, and if so, is it worth it for the occasional user? Are there now better platforms for “improving” authored texts? I have been using DeepL to edit blogposts or give them a snappy headline but it tends to make them a bit bland, maybe thats inevitable?
You say what you've said. If you dont like it then you ask it again to tone it up or down.
Exactly … plus I would also recommend Perplexity … I’m now using it far more than ChatGpt4o and it’s free.
Questions for those of you who are comfortable with using the freely available platforms.
I have to write a fairly formal report on a serious topic. My style has always been a bit racy. What would I say to ChatGPT to make my text more suitable for a conservative business audience? And what is the difference between standard ChatGPT and GPT4, and is the latter a subscription platform, and if so, is it worth it for the occasional user? Are there now better platforms for “improving” authored texts? I have been using DeepL to edit blogposts or give them a snappy headline but it tends to make them a bit bland, maybe thats inevitable?
You need to give ChatGPT a "role". That way, the responses you get will be better tailored to the output you require. So, for example, you might use a prompt that starts, "You are an expert in international business and you must provide responses which will clearly provide information and advice to conservative business audiences..." and then complete the prompt. That way your response from ChatGPT will most closely match the tone, content and depth you're looking for.
One great way to do this is, of course, to ask ChatGPT. So you could ask Chat GPT, "what would be the best prompt I could use to ask ChatGPT to provide me with information that is both expert and easy-to-understand by a conservative business audience?".
That's one of the great things about ChatGPT: it's an expert in everything, including how to converse with ChatGPT.
I did a load of shortlisting last week. So many candidates clearly used chat gpt or similar for their statements. I'm sorry you've worked in catering all your life, how did you acquire this detailed knowledge of adult safeguarding case law? Job applications are where artificial intelligence meets authentic stupidity.
I did a load of shortlisting last week. So many candidates clearly used chat gpt or similar for their statements. I'm sorry you've worked in catering all your life, how did you acquire this detailed knowledge of adult safeguarding case law? Job applications are where artificial intelligence meets authentic stupidity.
It’s painful sifting job applications when question answers are structured identical (and in some cases, every word)
I have to write a fairly formal report on a serious topic. My style has always been a bit racy.
Well he’s not known as the Jackie Collins of Central European Advertising for nothing!
It goes back to when I was a marketing trainee at United Biscuits. The Group Training Manager looked after us, and I had a bit of a teenage crush on her, which was a bit sad given I must have been about 20 by then. I did an HR project for her (actually assessing applications for the trainee scheme) and wrote a report. She considered it and said "the contents are good, but the style is a bit racy, like something for the Daily Mirror. I think you might be a frustrated journalist". I was suitability crushed, and did my best to follow my guardian angel's guidance, with mixed results🤣. She was wonderful though, of the age before "HR" was invented. Now I'm having a laugh at the HR managers who thought they could save money on recruitment consultants by doing it all directly on LinkedIn, only to find out that now a machine is going to do all that and carry out the selection process too.
Also, do you (does anyone) know the extent to which ChatGPT is available in other languages?
I don't use ChatGPT, I use Poe, but it's just as good in Chinese and shit's all over Google Translate for translating stuff too, which can be really handy when sharing work with coworkers.
I'm looking at it now. I understand that it's something from the Quora people and that it's able to connect not just to ChatGPT but several other models too, to generate answers. But it offers what at first sight are a dizzying array of bots that people have used the platform to create - is that right?.
I'd be interested to learn more about how you use it , Stu. Do you generally submit a question directly in the box like with ChatGPT, or have you selected some of those bots to use? Specifically how do you work with it for language translation?
It does seem to open up (yet another) whole new world of possibilities, but I wonder how one works out which of those bots are worth using, apart from just trial and error. I'm looking at one there that would tart up Powerpoint slides. I could definitely use that, I'm useless at it, since I rarely had to use it professionally.
Well a week is a long time in AI and after a beer this time last week with a mate who is well up on this stuff, and I am liking Claude for things that Chat GPT can do - friendlier interface, good on translation - and Perplexity, a much better alternative to Google for search. You can ask it a question such as “ pros and cons of all -weather tyres vs summer/winter tyre change“ and it will give you a coherent answer in proper usable language, and always shows you its sources. Great if you need to brief yourself before wading into some discussion that requires facts.
However I‘m still looking for something that can turn texts in bullet point format into a PowerPoint presentation. Anyone doing that task regularly, got a tip for that?
Also, do you (does anyone) know the extent to which ChatGPT is available in other languages?
I don't use ChatGPT, I use Poe, but it's just as good in Chinese and shit's all over Google Translate for translating stuff too, which can be really handy when sharing work with coworkers.
I'm looking at it now. I understand that it's something from the Quora people and that it's able to connect not just to ChatGPT but several other models too, to generate answers. But it offers what at first sight are a dizzying array of bots that people have used the platform to create - is that right?.
I'd be interested to learn more about how you use it , Stu. Do you generally submit a question directly in the box like with ChatGPT, or have you selected some of those bots to use? Specifically how do you work with it for language translation?
It does seem to open up (yet another) whole new world of possibilities, but I wonder how one works out which of those bots are worth using, apart from just trial and error. I'm looking at one there that would tart up Powerpoint slides. I could definitely use that, I'm useless at it, since I rarely had to use it professionally.
I mostly just use the poe assistant, although as I’m getting ‘better’ at using it, full ChatGPT is getting a lot more attractive.
For PPTs I’m lucky enough that my co homeroom teacher is very handy with PPTs and loves making them, so we just trade work.
As for translation i literally just type “translate this into Chinese / Russian / French” etc, with Chinese I’ll have it touched up, for French and Russian I just go with what I’m giving and have the two students laugh at the very few mistakes, although it’s noticeable how much better it’s got over the last year.
You bring up a fascinating point about emotional attachment to a team of players we’ve never personally met. It does seem odd that we can feel such a strong sense of achievement or disappointment based on the actions of individuals we don’t know personally. Yet, this is a common experience among sports fans across the world.
This emotional investment stems from social identity theory, which explains how fans often align their own identity with that of their team. In this framework, people don't just support a team—they feel a sense of belonging and pride in being part of the larger group of fans. Successes and failures of the team are seen as part of the collective experience, and in some ways, fans do feel a shared achievement or failure, even though they aren't on the field themselves.
There’s also something to be said for the idea of vicarious achievement, where fans celebrate a team’s success as if it were their own, gaining a kind of shared pride. While it might sound illogical from the outside, it plays into deeper psychological factors, like group solidarity and the need for affiliation with something greater than oneself. Fans often form strong emotional bonds with teams because they represent more than just the individuals playing—they represent a collective, a community, a history, and even personal memories or local pride.
That said, it can be a bit of a paradox—feeling a sense of achievement through a team you don't directly contribute to. It’s something that can feel irrational, but it's deeply ingrained in the way humans form connections with groups and identify with shared goals and struggles.
Do you think this attachment to a team helps or hinders you emotionally, given that there is this distance between the fans and players themselves?
I’m in the software industry, and whilst I spent a long time as a skeptic around AI, it’s clear that big businesses are going all in with it.
As for my personal use, I’m using ChatGPT more regularly nowadays but more for statistical problem solving, financial planning etc. Basically things that I wouldn’t realistically be able to do with just my brain.
I personally find the idea of people using the stuff for every tiny little thing quite concerning. Individual flair, and indeed error and interpretation, is something that is part of everyday life. If we’re all just making perfectly made points and masquerading our knowledge in ways that we haven’t structured ourselves, then something is being lost IMO.
That said, I was at a conference in the US last year and AI was one of a number of themes. It’s very clear that a number of successful and influential people in the tech industry are adamant that this is going to change the world to the similar extremes as the invention of the desktop computer and the internet. At the rate of adoption and investment, I’d be inclined to agree.
I’m in the software industry, and whilst I spent a long time as a skeptic around AI, it’s clear that big businesses are going all in with it.
As for my personal use, I’m using ChatGPT more regularly nowadays but more for statistical problem solving, financial planning etc. Basically things that I wouldn’t realistically be able to do with just my brain.
I personally find the idea of people using the stuff for every tiny little thing quite concerning. Individual flair, and indeed error and interpretation, is something that is part of everyday life. If we’re all just making perfectly made points and masquerading our knowledge in ways that we haven’t structured ourselves, then something is being lost IMO.
That said, I was at a conference in the US last year and AI was one of a number of themes. It’s very clear that a number of successful and influential people in the tech industry are adamant that this is going to change the world to the similar extremes as the invention of the desktop computer and the internet. At the rate of adoption and investment, I’d be inclined to agree.
I'm in the software industry as well. And 99% of of AI is bullshit. The 1% that isn't will be literally game changing - and not in a good way.
There is nothing to be excited about with AI - only worried.
I’m in the software industry, and whilst I spent a long time as a skeptic around AI, it’s clear that big businesses are going all in with it.
As for my personal use, I’m using ChatGPT more regularly nowadays but more for statistical problem solving, financial planning etc. Basically things that I wouldn’t realistically be able to do with just my brain.
I personally find the idea of people using the stuff for every tiny little thing quite concerning. Individual flair, and indeed error and interpretation, is something that is part of everyday life. If we’re all just making perfectly made points and masquerading our knowledge in ways that we haven’t structured ourselves, then something is being lost IMO.
That said, I was at a conference in the US last year and AI was one of a number of themes. It’s very clear that a number of successful and influential people in the tech industry are adamant that this is going to change the world to the similar extremes as the invention of the desktop computer and the internet. At the rate of adoption and investment, I’d be inclined to agree.
I'm in the software industry as well. And 99% of of AI is bullshit. The 1% that isn't will be literally game changing - and not in a good way.
There is nothing to be excited about with AI - only worried.
Would AI have spotted your double "of"?
Totally spoilt the post for me. Was gonna give it a "like" as well. ;-)
GenAI helps if you are not very good at e.g. French or music and need to understand something in French or produce a sound track for a home video. Or haven't got time to work out the Excel formula for mortgage repayments.
It gets a bit scarier when it is used to provide content on the web, without warning it is AI generated.
My son is no. 19 in his football team, so entered into Google "famous number 19 football players". The top result was:
@Arthur_Trudgill I asked something about why I still care despite living in another country for 20 years.
On this point chatgpt is incredible.
I asked it to give me one sentence for each of the following French verbs. These verbs are an example of a group of different but difficult vowel sounds for English speakers:
Étendre - to hang up / out
Entendre - to hear
Atteindre - to reach
Attendre- to wait
Éteindre - to turn off (lights only)
It did so perfectly. I then asked it to listen to me say the sentences and comment on my pronunciation.
I also practised the final sentence ’Remember to turn off the lights when you leave the room’ in Spanish.’
I had a 10 minute free trial with chatgpt version 4 and I have to say that she was like speaking to a real patient language speaker. She was also able to separate each sound in each syllable.
When I changed to the free version, it was good but it sounded more like an American speaking French and due to my accent she kept speaking to me in English despite explicitly saying that I wanted not to.
@Leroy Ambrose It is worrying given that I run a small English language training business. I think AI will replace many workers in a relatively short time frame - by 2040 certainly, some by 2030 or before. I include in this list some of the work of highly qualified jobs like doctors. I think practical jobs / trademen will be safe for a long time.
Ultimately, it will cause high unemployment I think. If we take a socialist approach then AI will free us all to have more leisure time. In reality, in this capitalist and ever more dystopian world, it will lead to poverty and civil unrest.
I’m in the software industry, and whilst I spent a long time as a skeptic around AI, it’s clear that big businesses are going all in with it.
Small businesses too. I have one client who has implemented it into his 40 employee business massively apparently. He says that he halved his work load. I’m also starting to use it to help prepare my lessons.
@Arthur_Trudgill I asked something about why I still care despite living in another country for 20 years.
On this point chatgpt is incredible.
I asked it to give me one sentence for each of the following French verbs. These verbs are an example of a group of different but difficult vowel sounds for English speakers:
Étendre - to hang up / out
Entendre - to hear
Atteindre - to reach
Attendre- to wait
Éteindre - to turn off (lights only)
It did so perfectly. I then asked it to listen to me say the sentences and comment on my pronunciation.
I also practised the final sentence ’Remember to turn off the lights when you leave the room’ in Spanish.’
I had a 10 minute free trial with chatgpt version 4 and I have to say that she was like speaking to a real patient language speaker. She was also able to separate each sound in each syllable.
When I changed to the free version, it was good but it sounded more like an American speaking French and due to my accent she kept speaking to me in English despite explicitly saying that I wanted not to.
@Leroy Ambrose It is worrying given that I run a small English language training business. I think AI will replace many workers in a relatively short time frame - by 2040 certainly, some by 2030 or before. I include in this list some of the work of highly qualified jobs like doctors. I think practical jobs / trademen will be safe for a long time.
Ultimately, it will cause high unemployment I think. If we take a socialist approach then AI will free us all to have more leisure time. In reality, in this capitalist and ever more dystopian world, it will lead to poverty and civil unrest.
Thanks jimmymelrose. I guessed something like "why are football fans so passionate about their teams" and tried it in plain Google to see if I could get something similar to what ChatGPT gave you. It sort of did but hard to tell if it's what you were looking for.
I admit I'm in the AI-sceptic camp, but I'm interested to hear how people get value from it. I am yet to have a good interaction with the tool, but I'll keep trying.
My other half used it at work to find out what a pipe was in the kitchen. Took a picture uploaded it and asked Chatgpt what the pipe was for and why would it be smelly. Told her exactly the right answer and gave options to resolve the whiff.
I’m in the software industry, and whilst I spent a long time as a skeptic around AI, it’s clear that big businesses are going all in with it.
As for my personal use, I’m using ChatGPT more regularly nowadays but more for statistical problem solving, financial planning etc. Basically things that I wouldn’t realistically be able to do with just my brain.
I personally find the idea of people using the stuff for every tiny little thing quite concerning. Individual flair, and indeed error and interpretation, is something that is part of everyday life. If we’re all just making perfectly made points and masquerading our knowledge in ways that we haven’t structured ourselves, then something is being lost IMO.
That said, I was at a conference in the US last year and AI was one of a number of themes. It’s very clear that a number of successful and influential people in the tech industry are adamant that this is going to change the world to the similar extremes as the invention of the desktop computer and the internet. At the rate of adoption and investment, I’d be inclined to agree.
I'm in the software industry as well. And 99% of of AI is bullshit. The 1% that isn't will be literally game changing - and not in a good way.
There is nothing to be excited about with AI - only worried.
I’m in the software industry, and whilst I spent a long time as a skeptic around AI, it’s clear that big businesses are going all in with it.
As for my personal use, I’m using ChatGPT more regularly nowadays but more for statistical problem solving, financial planning etc. Basically things that I wouldn’t realistically be able to do with just my brain.
I personally find the idea of people using the stuff for every tiny little thing quite concerning. Individual flair, and indeed error and interpretation, is something that is part of everyday life. If we’re all just making perfectly made points and masquerading our knowledge in ways that we haven’t structured ourselves, then something is being lost IMO.
That said, I was at a conference in the US last year and AI was one of a number of themes. It’s very clear that a number of successful and influential people in the tech industry are adamant that this is going to change the world to the similar extremes as the invention of the desktop computer and the internet. At the rate of adoption and investment, I’d be inclined to agree.
I'm in the software industry as well. And 99% of of AI is bullshit. The 1% that isn't will be literally game changing - and not in a good way.
There is nothing to be excited about with AI - only worried.
I am interested to know why you think that.
Let me see...
Technology is invented which may eventually make 30-40% of jobs redundant. How's that going to work out? Companies going to continue to employ people to do nothing? Or going to maximise profit for shareholders?
Not to mention the horrendous dangers inherent in the spread of misinformation - people already can't tell fact from fiction online as it is, imagine when it's in a video apparently from their favourite celebrity?
Want another example? Machine learning and algorithms already horribly disadvantage minorities when it comes to mortgage applications, schooling and medical insurance. How about turning the entirety of that process over Artificial 'Intelligence'? That'll end well...
Comments
"Tone and manner reference: (paste it here). "
GPT4 is just a little better at reasoning. One thing about providing a reference to be wary of, is that it does tend to repeat words. So I'd try with and without.
There is a new beta version available to paid users called Canvas, where it opens the document in a side window and shows you its suggested changes live, rather than just chucking out a new version at you. I haven't really played with this yet, though.
GPT/AI is not that great at writing headlines. It struggles to put broad ideas across in one snappy thought - usually you end up with two or three messages bunched together. You can push it to do better by giving it constraints, but it's better to just take the ideas it throws out and write your own.
You’ve confirmed my experience re headlines. So the sub-editor will not be a completely redundant role for a while, then.
Also, do you (does anyone) know the extent to which ChatGPT is available in other languages?
It's available in a lot of languages but its fluency and accuracy are better in the wider spoken languages like English, French, Spanish, etc. It says it may have limited vocabulary / nuanced cultural context in others.
One great way to do this is, of course, to ask ChatGPT. So you could ask Chat GPT, "what would be the best prompt I could use to ask ChatGPT to provide me with information that is both expert and easy-to-understand by a conservative business audience?".
That's one of the great things about ChatGPT: it's an expert in everything, including how to converse with ChatGPT.
I'd be interested to learn more about how you use it , Stu. Do you generally submit a question directly in the box like with ChatGPT, or have you selected some of those bots to use? Specifically how do you work with it for language translation?
It does seem to open up (yet another) whole new world of possibilities, but I wonder how one works out which of those bots are worth using, apart from just trial and error. I'm looking at one there that would tart up Powerpoint slides. I could definitely use that, I'm useless at it, since I rarely had to use it professionally.
Would anyone like to answer the final questions?
It said it could be a draw or either side could win. Genius.
I personally find the idea of people using the stuff for every tiny little thing quite concerning. Individual flair, and indeed error and interpretation, is something that is part of everyday life. If we’re all just making perfectly made points and masquerading our knowledge in ways that we haven’t structured ourselves, then something is being lost IMO.
There is nothing to be excited about with AI - only worried.
Totally spoilt the post for me. Was gonna give it a "like" as well.
;-)
It gets a bit scarier when it is used to provide content on the web, without warning it is AI generated.
My son is no. 19 in his football team, so entered into Google "famous number 19 football players". The top result was:
https://kingsoccertips.com/soccer-players-number-19/
Which omits Lamine Yamal, but includes these two amusing descriptions:
@Arthur_Trudgill
I asked something about why I still care despite living in another country for 20 years.
On this point chatgpt is incredible.
I asked it to give me one sentence for each of the following French verbs. These verbs are an example of a group of different but difficult vowel sounds for English speakers:
Étendre - to hang up / out
Entendre - to hear
Atteindre - to reach
Attendre- to wait
Éteindre - to turn off (lights only)
It did so perfectly. I then asked it to listen to me say the sentences and comment on my pronunciation.
I also practised the final sentence ’Remember to turn off the lights when you leave the room’ in Spanish.’
I had a 10 minute free trial with chatgpt version 4 and I have to say that she was like speaking to a real patient language speaker. She was also able to separate each sound in each syllable.
When I changed to the free version, it was good but it sounded more like an American speaking French and due to my accent she kept speaking to me in English despite explicitly saying that I wanted not to.
@Leroy Ambrose
It is worrying given that I run a small English language training business. I think AI will replace many workers in a relatively short time frame - by 2040 certainly, some by 2030 or before. I include in this list some of the work of highly qualified jobs like doctors.
I think practical jobs / trademen will be safe for a long time.
Ultimately, it will cause high unemployment I think. If we take a socialist approach then AI will free us all to have more leisure time. In reality, in this capitalist and ever more dystopian world, it will lead to poverty and civil unrest.
I’m also starting to use it to help prepare my lessons.
I admit I'm in the AI-sceptic camp, but I'm interested to hear how people get value from it. I am yet to have a good interaction with the tool, but I'll keep trying.
I am interested to know why you think that.
Technology is invented which may eventually make 30-40% of jobs redundant. How's that going to work out? Companies going to continue to employ people to do nothing? Or going to maximise profit for shareholders?
Not to mention the horrendous dangers inherent in the spread of misinformation - people already can't tell fact from fiction online as it is, imagine when it's in a video apparently from their favourite celebrity?
Want another example? Machine learning and algorithms already horribly disadvantage minorities when it comes to mortgage applications, schooling and medical insurance. How about turning the entirety of that process over Artificial 'Intelligence'? That'll end well...