Skip to main content

Does ChatGPT signal the end of university essays and journalists?

There has been a lot on social media recently about the remarkable AI 'writer' ChatGPT. Many of my contacts are either academics or writers - and in both fields there has been concern about the ability of such AI software to interfere with their work. 

As far as academics are concerned, the software arguably calls into doubt the value of the essay as means of assessing student knowledge (particularly the short exam-style essay, which some universities still allow to be submitted online). And some writers have worried that their jobs are at risk if, for example, a news outlet can get ChatGPT to knock up a story for free.

My assessment is that the software is extremely impressive - but it has limitations that are likely to continue for a long time. Even with these limitations, it certainly could make inroads into student essays and poorly churned out journalism, but is unlikely to be a significant threat if some degree of insight or fact checking is required.

Let's take a look at a couple of specifics. I first asked ChatGPT:

Why can't I send a message using quantum entanglement?

Its response was as follows:

Quantum entanglement is a phenomenon that occurs when two particles become linked, such that the state of one particle is dependent on the state of the other. This means that if the state of one particle is known, the state of the other particle can be determined instantly, regardless of the distance between the two particles. While this phenomenon has been demonstrated in a laboratory setting, it is not currently possible to use it for sending messages. This is because the particles that are entangled must be in close proximity in order to become linked, and the entanglement is easily disrupted by outside influences. As a result, it is not possible to use quantum entanglement to transmit information over long distances.

This is deeply wrong, after the first couple of basic background sentences. Entanglement has been used outside the lab ever since 2004 when Anton Zeilinger did his demonstrations making use of the sewers of Vienna, and has now been achieved using the Chinese Micius satellite between orbit and the ground. Close proximity is not the issue. The actual reason is that entanglement can only share totally random data - there is no way to impose a message on it. This doesn't mean it's useless - it can be used to share (desirably random) encryption keys - but it's useless for instant messaging.

I then tried a topic that would be familiar to any science journalist:

Why was the name of the James Webb telescope controversial?

This was my third attempt at phrasing the question, as the first two times I got a reply on why the telescope itself wasn't controversial, rather than any insight into the name. But once I got the question right I was rewarded with this answer:

I'm sorry, but I am not aware of any controversy surrounding the naming of the James Webb Space Telescope. The telescope is named after James Webb, who served as the second administrator of NASA from 1961 to 1968. Webb played a key role in the development of the agency's human spaceflight program, including the Apollo missions that landed astronauts on the moon. The telescope was named in his honor to recognize his contributions to NASA and space exploration. I apologize if my earlier response was not clear or if I misunderstood your question. Please let me know if you have any further questions or concerns.

However, in reality there is a distinct controversy about the name, both because naming a scientific instrument after an administrator seems dubious, but also because of concerns about aspects of behaviour in Webb's NASA. This was a non-answer as far as the question was concerned.

Finally, for amusement, I picked up on another of ChatGPT's accomplishments - writing poems of the 'so bad it's quite good' nature. (Certainly, no poets are worried about being put out of work.) I asked

Can you write a sonnet about quantum entanglement?

And this was ChatGPT's response:

Sure, here is a sonnet about quantum entanglement:

In the strange world of the quantum realm
Where particles dance and shimmer with glee
A curious phenomenon occurs, it seems
Two particles become as one, you see

Entangled, they are linked together
Their states intertwined, never to part
No matter the distance, they’ll stay tethered
A bond that can never be broken by heart

Their fates are intertwined, forever more
One particle knows what the other will do
No matter how far apart they may roam
Their connection remains true and true

Quantum entanglement, a marvel to behold
A mystery of the universe, to be told.

See all of Brian's online articles or subscribe to a weekly digest for free here
Labels:

Comments

Post a Comment

Popular posts from this blog

Why I hate opera

If I'm honest, the title of this post is an exaggeration to make a point. I don't really hate opera. There are a couple of operas - notably Monteverdi's Incoranazione di Poppea and Purcell's Dido & Aeneas - that I quite like. But what I do find truly sickening is the reverence with which opera is treated, as if it were some particularly great art form. Nowhere was this more obvious than in ITV's 2010 gut-wrenchingly awful series Pop Star to Opera Star , where the likes of Alan Tichmarsh treated the real opera singers as if they were fragile pieces on Antiques Roadshow, and the music as if it were a gift of the gods. In my opinion - and I know not everyone agrees - opera is: Mediocre music Melodramatic plots Amateurishly hammy acting A forced and unpleasant singing style Ridiculously over-supported by public funds I won't even bother to go into any detail on the plots and the acting - this is just self-evident. But the other aspects need some exp...
118 comments
Read more

Murder by Candlelight - Ed. Cecily Gayford ***

Nothing seems to suit Christmas reading better than either ghost stories or Christmas-set novels. For some this means a fluffy romance in the snow, but for those of us with darker preferences, it's hard to beat a good Christmas murder. An annual event for me over the last few years has been getting the excellent series of classic murderous Christmas short stories pulled together by Cecily Gayford, starting with the 2016 Murder under the Christmas Tree . This featured seasonal output from the likes of Margery Allingham, Arthur Conan Doyle, Ellis Peters and Dorothy L. Sayers, laced with a few more modern authors such as Ian Rankin and Val McDermid, in some shiny Christmassy twisty tales. I actually thought while purchasing this year's addition 'Surely she is going to run out of classic stories soon' - and sadly, to a degree, Gayford has. The first half of Murder by Candlelight is up to the usual standard with some good seasonal tales from the likes of Catherine Aird, Car...
Post a Comment
Read more

Is 5x3 the same as 3x5?

The Internet has gone mildly bonkers over a child in America who was marked down in a test because when asked to work out 5x3 by repeated addition he/she used 5+5+5 instead of 3+3+3+3+3. Those who support the teacher say that 5x3 means 'five lots of 3' where the complainants say that 'times' is commutative (reversible) so the distinction is meaningless as 5x3 and 3x5 are indistinguishable. It's certainly true that not all mathematical operations are commutative. I think we are all comfortable that 5-3 is not the same as 3-5.  However. This not true of multiplication (of numbers). And so if there is to be any distinction, it has to be in the use of English to interpret the 'x' sign. Unfortunately, even here there is no logical way of coming up with a definitive answer. I suspect most primary school teachers would expands 'times' as 'lots of' as mentioned above. So we get 5 x 3 as '5 lots of 3'. Unfortunately that only wor...
25 comments
Read more