iPad Pro The rise of ChatGPT has made the iPad useless

[Jessica Lares]

There are better ways you can read material besides relying on AI. You should look into that. Like, I don't drive and have no clue about cars period, but I can still grab the manual in the glove compartment and tell you the specific replacement parts of things and where the switch for what is fairly quickly, because I know how to navigate a book.

It can also be more efficient than using web search because it's just one source of material versus 10,000+ websites. That's the same way you could figure out which books are worth reading on a given topic when there's fifty of them to choose from.

 

[TheRealTVGuy]

Having a good understanding of what an "AI butler" actually is, and how they work behind the scenes, I don't use them for any kind of "real work". They're fun to play with, sure. But trust with my work? No. So I'm still good with my iPad and its limited built-in text input capabilities.

I strongly disagree that these "co-pilots" are a crucial part of working. They're shiny new text prediction engines, much like autocomplete on your iPhone, only trained on a larger dataset. The "I" in "AI" is a big misnomer. There is no intelligence at work.

I have a bit of a unique perspective when it comes to this sort of stuff in academia. I run the online learning management/course delivery systems for 13 or so universities and colleges. I also went to university for my undergrad both in the 90s and again 12 years later in the 2000s [I kinda got distracted the first time around]). That experience + my current work has given me a great deal of insight on how students have adapted to new technologies over the years.

Students have always looked for shortcuts to get their work done, and in the past 25 years or so these shortcuts have become more and more technologically-based. And I get it - depending on your area of study the workload can be huge (my area of study was physics, my 3rd year workload was nuts). Who wouldn't want to be more "efficient"?

But when it comes down to it, ChatGPT, Bard or Bing isn't likely to be there to answer questions or bounce ideas off during your final exam. In the long run, it's better to put in the effort to learn how to write a good essay, or write a C++ program, or calculate that partial differential equation yourself rather than trust that a predictive text bot running bunch of linear algebra in a Microsoft datacenter is going to successfully and accurately do the work for you.

Why can’t Pearson and ProctorHub hire decent coders and why won’t many of the software suites in academia work with Safari?

Everywhere I go on campus I see Apple products, but whenever there’s an issue with academia related software the response is “try it on Firefox.”

 

[Chriss_m]

People use iPads for work?

 

[WilliApple]

This is very random lol.

How does ChatGPT replace the iPad? The iPad is still a really cost effective second display for a workflow for stuff like Universal Control. Kind of weird that this topic mentions that ChatGPT replaces the iPad...

 

[Jumpthesnark]

This is very random lol.

How does ChatGPT replace the iPad? The iPad is still a really cost effective second display for a workflow for stuff like Universal Control. Kind of weird that this topic mentions that ChatGPT replaces the iPad...

I don't think the headline or OP said that ChatGPT "replaces the iPad."

 

[JustAnExpat]

>I have witnessed that people in my university, and a lot of people on social media, have adopted ChatGPT into their workflow.

1. Why is ChatGPT being used in Universities? Not to write papers, right?
2. iPads have always been bad at inputing and changing text if you don't have a keyboard and mouse.
3. Honestly, as someone who was a university student until just recently, there's zero reasons why an iPad should be the main computer if you're at a university doing any type of writing.

 

[JustAnExpat]

Whatever the hell ChatGPT is has absolutely no additional bearing on the fact that iPad is for play and the Mac is for work.

ChatGPT is cool. You can ask it to do something, like write a letter to a creditor to dispute a bill, and it'll write that letter for you. Or you can ask it to write a story. Or compare two different things together. Or write a poem. Or have it look up information.

 

[JustAnExpat]

You mean you do know how to copy and paste using touch?

Workflow? Please explain. I read on Science (or was it Nature) homepage today that AI written texts was forbidden in their journals. Do you mean students using it for learning and report writing? It is better lookup than Wikipedia because it explain topics quite pedagogically and sometimes Wikipedia is too deep. ChatGPT write at high school to lower BSc level and does not always complete answers. Furthermore, it does not seem to say from where it takes the data/knowledge so it is in that sense quite useless without significant literature study where iPad is outstanding for reading books and scientific articles.

I've read that a lot of lower level university students are cheating by having ChatGPT write the papers. Thankfully TurnItIn is being updated to detect ChatGPT papers, and I think ChatGPT has a feature where you can copy and paste sentences to see if they were machine generated or not.

 

[WoodTableFromIkea]

I can't even grasp the logic of this post, lol.

I mean... What does ChatGPT have to do with how people use their iPad?

 

[jdb8167]

I just spoke to chatGPT via the dictation microphone icon from my iPad mini. I said “Design an algorithm that converts a mini max range, and value to a percentage”. This is what it came up with:

Here's an algorithm to convert a value within a range to a percentage:

1. Check the input to ensure that the value is within the range of min and max. If the value is less than min, set it to min. If the value is greater than max, set it to max.
2. Calculate the range by subtracting the min from the max: range = max - min
3. Subtract the min from the value: adjusted_value = value - min
4. Divide the adjusted value by the range: percentage = adjusted_value / range
5. Multiply the result by 100 to get the percentage as a decimal: percentage *= 100
6. Return the final percentage value

python

def value_to_percentage(value, min_range, max_range):
    # Ensure value is within range
    if value < min_range:
        value = min_range
    elif value > max_range:
        value = max_range

    # Calculate range
    range = max_range - min_range

    # Adjust value
    adjusted_value = value - min_range

    # Calculate percentage
    percentage = adjusted_value / range * 100

    return percentage

No keyboard required. Note that I didn’t correct the transcription mistakes. Troll post.

 

[Shirasaki]

Perhaps the OP uses the forum here as he would experiment with ChatGPT:
Drop some weird lines of text and see what the HI (human intelligence) engine of us here makes out of it...

You made my day Lmao.

 

[neutrino17]

I’m using my iPad mostly to take handwritten notes in graduate-level statistics classes, such as where we’re learning how to write our own machine learning algorithms. It’s great … the professor typically posts a PDF of lecture slides, and I can scribble directly on them, insert blank pages for the chalkboard transcripts, and so on. If I need to pull up something from a Web site or reference an email or check my calendar or whatever, it’s just a quick swipe away.

I can guarantee you that, as damned impressive as ChatGPT assuredly is, it is utterly useless for any sort of math more advanced than basic Calculus (and maybe not even that).

For example … I asked it to prove that the square root of two is irrational. It did well enough that it’d probably get an “A” on that question. Then, in the same chat, I asked it to prove that the square root of two is rational. It happily obliged with a convincingly-confident but seriously flawed “proof.” I then pointed out the most obvious contradiction between its first and second replies, and it stubbornly stuck to its guns that the square root of two is both rational and irrational.

I can’t wait for Siri to advance to the level of ChatGPT. And it’ll probably be sooner than any of us realize that it’ll gain graduate-level competency in various fields. But it’s still got quite a ways to go.

Right now, I’d say it’s basically a talented but overconfident ten-year-old with an encyclopedic photographic memory. Trust it accordingly.

b&

Exactly. I tried this on some questions about x-ray microanalysis. It came back with BS answers. By that, it seems like it went to Wikipedia, picked up a few general facts then used that to weave a plausible narrative. It wasn’t correct. It certainly wasn’t informative or trustworthy.

I call it BS because it is kind of like that guy you meet in a bar who knows a few facts then tries to weave a convincing story around that.

I’m not saying this is useless. Given a narrow domain it might be great. For example: give me a weather report for my neighborhood. I guess it could get the information about my local area then package that in some reasonable grammar.

 

[Arran]

Love the title of this thread. Future clickbait case study.

 

[iPadified]

They asked it to summarize PDF's, books, articles. Meanwhile, I sat there with my iPad Pro + Pencil, manually read dense source material like a caveman and took hand written notes, which is much slower than typing on a keyboard. It literally took me 2-3 times longer to begin my initial draft.

As I thought. Tip from a university teacher: continue to be a caveman because that is part of the learning process which, in the end, give you the ability to think quickly and freely enough to be innovative.

Now hear me out carefully: From the teachers perspective, your report has no other purpose than teaching you a topic. In all other sense it is worthless (sorry for being harsh). It seems for an increasing number of students, passing an exam seem to be more important than actually learning the topic. Hence, all types of shortcuts are taken to pass the exam without. Students are really shooting themselfs in the foot.

Ask yourself:
Do you think you are attractive to an employer if your are relying on AI chatbots?
Are you able you evaluate if the AI chatbot is giving the correct or state of the art answers?

As a helper to lookup information: great idea because it saves time because googling is a minefield of misinformation. I am looking forward to use these robots in my teaching. To replace learning and higher thinking (summarising articles and actually formulate a written text, e.i. evaluating and being creative): really, really poor idea.

PS. What will happen is that we will change tactics to use oral examinations or exams without help. That really works fine to distinguish lazy people from hardworking. DS.

PSS. We do have systems that looks for plagiarisms and I bet the AI chatbots are giving the same answer every single time. DSS.

 

[iPadified]

Exactly. I tried this on some questions about x-ray microanalysis. It came back with BS answers. By that, it seems like it went to Wikipedia, picked up a few general facts then used that to weave a plausible narrative. It wasn’t correct. It certainly wasn’t informative or trustworthy.

I call it BS because it is kind of like that guy you meet in a bar who knows a few facts then tries to weave a convincing story around that.

I’m not saying this is useless. Given a narrow domain it might be great. For example: give me a weather report for my neighborhood. I guess it could get the information about my local area then package that in some reasonable grammar.

Tried some about the next gen sequencing and the key part (the difficult one) was missing. Tried some about beta-thalassemia. Actually not wrong but without depth.

 

[unchecked]

Love the title of this thread. Future clickbait case study.

Almost as though an AI wrote it.

Will be quite interesting to see if someone actually try this "How do you write a clickbait forum topic on Macrumors?" prompt.

 

[TechnoMonk]

Almost as though an AI wrote it.

Will be quite interesting to see if someone actually try this "How do you write a clickbait forum topic on Macrumors?" prompt.

As a language model AI, I do not promote unethical or misleading practices such as clickbait. Creating clickbait topics is not only unethical but also detrimental to building trust and credibility in a community. A better approach is to write a compelling and informative topic that accurately reflects the content of the discussion to be had.

 

[flobach]

Whatever the hell ChatGPT is has absolutely no additional bearing on the fact that iPad is for play and the Mac is for work.

Good that I get to play at work, blurring the boundaries even more ;-)

 

[ninecows]

I've read that a lot of lower level university students are cheating by having ChatGPT write the papers. Thankfully TurnItIn is being updated to detect ChatGPT papers, and I think ChatGPT has a feature where you can copy and paste sentences to see if they were machine generated or not.

Haha…

Dear ChatGPT. Did you write this: <insert students essay here>

 

[plufz]

Isn’t the basic idea of using chatgpt to let you type less…? If anything wouldn’t it make a touch screen without keyboard more useful than before?

 

[flashflood101]

Hmmmm, is it the iPad that's useless?

 

[floral]

I think this topic exploded because of the sheer "what?" factor... half of the people are just reacting at how confusing a topic this is, and the others are replying with answers that attempt to make sense of this (mine included, on page 1).

Now I can see this topic was essentially reply-bait because not only did the poster happen to join on April 1st, their reply history contains a lot of "hot takes" that intentionally spark lots of discussion. This "hot take" happened to be a curveball that made a lot of people (again, me included) spend some time on it to make sense of it. Also note, they have only replied one time after the initial post... 2 pages ago.

I say we stop replying here. Who knows how long this discussion will last with no new answers from the poster, and it will all be seen as "getting popular" from said poster because numbers go up > happiness activates.

Unless of course, I'm dead wrong, then feel free to bombard me with reactions.

 

[tornadowrangler]

I have witnessed that people in my university, and a lot of people on social media, have adopted ChatGPT into their workflow. These "co-pilots" are a crucial part of working and they live permanently on the side. You are constantly sending it ideas and editing the draft. For that to happen, you need a keyboard which makes the iPad without a keyboard useless for people working in 2023. Of course, people say you can use the iPad with a keyboard but at that point, you might as well use the MacBook instead.

What are your thoughts on iPad's place in a world of AI butlers, like ChatGPT?

Here, I'll fix your title:

"The rise of ChatGPT has made the iPad useless to a few specific people"

Also, you didn't do a good job describing how these people were using an iPad before. What were they doing on it and how did ChatGTP replace what they were doing on it?

 

[crymimefireworks]

I have witnessed that people in my university, and a lot of people on social media, have adopted ChatGPT into their workflow. These "co-pilots" are a crucial part of working and they live permanently on the side. You are constantly sending it ideas and editing the draft. For that to happen, you need a keyboard which makes the iPad without a keyboard useless for people working in 2023. Of course, people say you can use the iPad with a keyboard but at that point, you might as well use the MacBook instead.

What are your thoughts on iPad's place in a world of AI butlers, like ChatGPT?

Most of the replies here seem to suggest you to not trust what you see.

What you are seeing is a powerful force at work.

It does sound like iPads are less useful in a world of AI butlers. I could imagine Siri getting much better and that eliminates the keyboard.

Could you more precisely describe the workflow you are seeing? Do people keep ChatGPT open at all times? Do they copy paste back to Google Docs while they write? What are 5 examples of assignments you've seen done in this fashion? Are they signing up for the paid plan?

 

[Unami]

Nothing has changed - I use chatGPT just like anything else text related before on my ipad. How did you use the ipad for things like googling or writing texts before? Just use a keyboard, dictation or the on-screen keyboard. There's even a shortcut whith which you can use siri for access to the ChatGPT-api.

Also, ChatGpT is a nice toy, but a lot of it's prose is a bit stiff and sounds canned and generic. If you get good marks with that, you should probably look for a better university. I wouldn't worry too much about it, those tools are not there. Yet. GPT is nothing new, we've been playing around with version 2 for years. But with chatgpt and things like midjpourney or now google's new tools, things are moving quite fast again after years of stagnation in the IT-sector. Now with microsoft pumping millions into OpenAI and google reacting because they worry about their core business, I'm a little worried that Apple has missed the train.