By clicking “Accept All”, you agree to the storing of cookies on your device to enhance site navigation, analyse site usage, and assist in our marketing efforts
These cookies enable our website and App to remember things such as your region or country, language, accessibility options and your preferences and settings.
Analytic cookies help website owners to understand how visitors interact with websites by collecting and reporting information anonymously.
Marketing cookies are used to track visitors across websites. The intention is to display ads that are relevant and engaging for the individual user and thereby more valuable for publishers and third party advertisers.
Our system admin vetoed it for exactly this reason.How do you handle the confidentiality of information?
I imagine it would work really well. A machine reading the work of another machine.It does however raise the question of whether that stilted content actually works in SEO terms?
And then there is this:
![]()
Lawyers used ChatGPT to help with a case - it backfired massively
OpenAI's ChatGPT has wowed users with its ability to write essays and speeches, complete homework, crack computer code and pen poems - but it's also prone to completely making things up.news.sky.com
A LLM is fine for churning out generic copy if you just want to fill a page with junk. What it’s not very good at is writing factual information.
The school report thing is an example of how it can be used. But not if the report is to contain facts about the pupil.
From my experience of my daughters' reports from their secondary school it is obvious they are part auto generated anyway and chatgpt would make little difference - what i want is an actual report on my daughters' progress not a colour coded signal against an impossible benchmark and some meaningless auto generated twaddleA LLM is fine for churning out generic copy if you just want to fill a page with junk. What it’s not very good at is writing factual information.
The school report thing is an example of how it can be used. But not if the report is to contain facts about the pupil.
That sounds a bit like something created by AI??Quite a bit of critical replies here in this thread. Just for fun, I copy/pasted the replies and asked ChatGPT for a reaction. (see below). I put interesting sections in bold.
As an AI language model developed by OpenAI, I appreciate the feedback and criticism shared by all these users. It's essential to note that ChatGPT is not perfect and indeed can produce inaccurate responses or interpretations, especially when it comes to factual or detailed knowledge on specific subjects. The model does not have direct access to databases, so it does not "look up" facts but generates responses based on patterns it has learned from its training data.
Furthermore, as has been noted, I don't have the ability to provide the original sources for my responses because I generate them based on a mixture of licensed data, data created by human trainers, and publicly available data. Therefore, I don't have the ability to access or retrieve personal data unless it has been shared with me in the course of our conversation. I am designed to respect user privacy and confidentiality.
For math questions or complex calculations, while I strive to be as accurate as possible, errors can happen. This is an area that OpenAI is continually working on improving.
When it comes to content generation, whether humorous or not, I try to adapt to the input given, but the result might not always meet everyone's expectations. As mentioned, the quality of the generated content can greatly depend on the quality and clarity of the input.
The confidentiality of information and security are taken very seriously, and OpenAI implements strict measures to protect users' data. However, as with all digital tools, it is always advisable to avoid sharing sensitive information.
Finally, it's important to stress that I'm a tool intended to assist users by providing information, generating text, and automating certain tasks. I'm not a replacement for professional expertise in areas like legal, medical, financial, or other specialized fields.
The purpose of AI tools like me is not to replace humans but to aid them. That being said, it's important to critically evaluate the information provided by AI and make use of it judiciously.
Thank you for all your valuable feedback. It helps OpenAI in improving my capabilities and making me a better tool for users.
This all seems reasonable, except for the part on math questions or complex calculations. As a language model, I don't see how OpenAI can train the model on making calculations. Unless they connect it with something like WolframAlpha.
I don't want to miss out on the productivity enhancements that it can bring to the team.
Presumably that depends very much on what your team are going to use it for?Many interesting replies here, but I still have the question: "if and how to put this into the hands of my team".
Many people have asked me if they can use it and I don't want to miss out on the productivity enhancements that it can bring to the team.
It doesn't really answer our question, which revolves around are you giving professional advice?To answer some of the questions above, here is a list of questions we've experimented with:
I am aware there are many other ways to answer each of these questions, but all these gave reasonable answers to start from.
- what copyright or ownership notice should I add to my blog to prevent people from stealing/copying my content?
- Please correct any spelling or grammar mistakes in the following article.
- We get a customer complaint that his order was delivered late and contained the wrong items. What is the best way to approach this issue?
- What's the command to convert a KVM virtual machine into a VMWare workstation
- That client sent us a .gz file. How to read the contents of a .gz file
- What are some of the issues when a customer wants you to sign an exclusivity contract
Oh no, I am not giving paid professional advice.It doesn't really answer our question, which revolves around are you giving professional advice?
If you ae playing/exploring 'reasonable answers' is fine - if you are being paid for advice I'd say it's inadequate or potentially dangerous.
It's a bit of an odd one and a very interesting one. Based on your input inquiry, I got 493,827,100. Fair enough and a strange result. Since we use some AI frameworks for testing and teaching, I took a deeper look. I'm not sure why it came up like that, but if you input the inquiry like this:12345678 multiplied by 43 equals 531,440,154
Are you on GPT-3 or GPT-4 ? Version 4 seems to work just fine.Fatally bugged....
'fraid not! Close but no coconut
Calculate: 12,345,678 multiplied by 43
The product of multiplying 12,345,678 by 43 is:
12,345,678 * 43 = 530,864,754
I asked it to regenerate
Sure, let's calculate 12,345,678 multiplied by 43:
12,345,678 * 43 = 530,864,554
So, 12,345,678 multiplied by 43 is equal to 530,864,554.
Fatally bugged....
MS is baking AI into everything. It will become the de facto tool for all queries. Which means people will ask if to do calculations and many other things for which it’s not suitable.ChatGPT is a large language model, which means it is not designed for performing calculations.
We looked at this but really not ideal for our sector yet.I've used it for quickly rewriting badly translated product descriptions into better English.
I *could* do it myself, but I don't have the time.
My wife (a tech support engineer) has spent the last 2 days proof reading and editing the translation of the manual for their latest product (they are a distributor and it is a Chinese made piece of specialist electronics), it needed both decent English and an engineers understanding of how the product is used to be able to produce an end product that with save users ringing them rather than cause more work.We looked at this but really not ideal for our sector yet.
My wife (a tech support engineer) has spent the last 2 days proof reading and editing the translation of the manual for their latest product (they are a distributor and it is a Chinese made piece of specialist electronics), it needed both decent English and an engineers understanding of how the product is used to be able to produce an end product that with save users ringing them rather than cause more work.