ChatGPT: implications for teaching, how it analyses Brexit and the link to Psychoanalysis

April 27, 2023

     By Duncan Green     

ChatGPT. Discuss. Isn’t everyone? Right now, everyone seems to be playing with it, writing and/or worrying about it and with good reason. Some are already losing their jobs after publishing faked interviews.

Good luck with that

There are refuseniks – this is crowdsourced plagiarism and must be kept at bay. Students must not use it. Massive health warnings etc etc. That feels both King Canute-ish and a missed opportunity.

I’m in the engagement camp – how do we use AI to save time and make us smarter? Seems to me it can at the very least act as a kind of personalized Wikipedia – a new starting point, on the basis of which you or your students can then train your critical eye, fact check (it does make a lot of stuff up!), spot gaps and critique (which as far as I know it can’t do) and save a lot of time. AI geek Rowan Cheung has a nice tweet highlighting 5 main uses: brainstorming, summarizing, rewriting for a beginner, changing the style (e.g. to James Joyce or Donald Trump), or edit my work.

From the teaching point of view, it’s hard to distinguish ChatGPT from an average student essay, but not impossible. LSE’s guidance is to look for passages that are:

  • Prone to Verbosity and Hyperbole
  • Often an absence of insight (critical analysis and evaluation)
  • Non sequiturs
  • Out of sequence numerical ranges
  • Sentences may contain alternating British and US spelling of words.
  • Lack of flow.
  • Differently phrased repetition
  • Padded sentences.
  • Random archaic words not generally used (jeremiad)
  • Factually incorrect
  • Draws on non-existent sources.
  • References irrelevant / unavailable / old /

(I want to point out here that any similarity to my writing does not mean I’m a bot. But then it would say that, wouldn’t it?)

I asked ChatGPT (which is insanely user friendly by the way) ‘Using Stephen Lukes framework of visible, hidden and invisible power, explain the factors that led to the 2016 Brexit vote in the UK’ and got:

‘Stephen Lukes’ framework of power distinguishes between three dimensions of power: visible power, hidden power, and invisible power. Visible power refers to the ability to make decisions and enforce them through the use of authority, coercion, or force. Hidden power refers to the ability to shape the agenda and influence decision-making through the control of information, resources, or access to decision-makers. Invisible power refers to the ability to shape people’s preferences and beliefs, and to control the terms of public debate, so that certain issues are excluded or marginalized.

The 2016 Brexit vote in the UK was the result of a complex interplay of factors, which can be analyzed using Lukes’ framework of power:

Visible power: The decision to hold a referendum on EU membership was made by the UK government, led by the Conservative Party. The government had the power to set the terms of the referendum, including the question that was put to the electorate. However, the government failed to anticipate the consequences of the referendum, and the result was a shock to many in the political establishment.

Hidden power: The Brexit campaign was supported by a range of actors, including media outlets, think tanks, and wealthy individuals, who were able to shape public opinion and influence decision-making through their control of resources and access to decision-makers. For example, many of the newspapers that supported Brexit are owned by wealthy individuals who have close ties to the Conservative Party. This allowed them to shape the agenda and control the terms of public debate, framing the issue as one of national sovereignty and immigration control.

Invisible power: The Brexit vote was also influenced by deeper social and cultural factors, such as the growing sense of alienation and disaffection among many working-class voters, who felt that they had been left behind by globalization and the political establishment. This sense of disenfranchisement was fueled by the decline of traditional industries, the erosion of job security, and the perceived threat posed by immigration. These factors created a fertile ground for the anti-EU message of the Brexit campaign, which promised to restore control to the UK and protect its borders.

In conclusion, the 2016 Brexit vote in the UK was the result of a complex interplay of visible, hidden, and invisible power. While the government had the power to set the terms of the referendum, the outcome was shaped by the influence of powerful actors who were able to control the agenda and shape public opinion. At a deeper level, the Brexit vote was also driven by social and cultural factors that reflected a sense of alienation and disaffection among many voters.’

Nothing actually wrong, as far as I can see, but the content is pretty average. The art with AI is clearly going to lie in the follow-up questions you ask.

Best thing I’ve read about it so far is this wonderful essay in The Economist, comparing AI to the invention of the browser, the printing press and practice of psychoanalysis.

The psychoanalysis analogy is particularly memorable, providing new ways to think about AI, including:

‘Winkling out non-conscious biases acquired in the pre-verbal infancy of training; dealing with the contradictions behind hallucinations; regularising rogue desires: ideas from psychotherapy might be seen as helpful analogies for dealing with the pseudocognitive AI transition even by those who reject all notion of an AI mind. A concentration on the relationship between parents, or programmers, and their children could be welcome, too. What is it to bring up an AI well? What sort of upbringing should be forbidden? To what extent should the creators of AIs be held responsible for the harms done by their creation?

AI is also happy to indulge a bit of tomfoolery. Back to Brexit ‘Please rephrase this analysis as rhyming couplets, haikus and a limerick’

Rhyming couplets:

‘The Brexit vote was wrought with power, Visible, hidden, at every hour. The UK government set the stage, But unseen forces played a sage.

Wealthy actors shaped the debate, Their influence hidden, hard to sate. Media outlets, think tanks galore, Controlled the message, to even the score.

Disaffection among working-class, Invisible power had come to pass. Sense of alienation, left behind, Brexit promised to restore, and bind.’


‘Brexit vote was swayed,

By power seen, unseen and played.

UK’s fate was made.’

Or my favourite

‘Invisible force,

Alienation, the source,

Brexit, their recourse.’

But its limericks (like mine) are rubbish:

‘The Brexit vote was full of power,

Both seen and unseen, it did tower.

The government set the stage,

But hidden forces were all the rage,

And disaffection proved to be its flower.’

Thoughts? Advice?

April 27, 2023
Duncan Green