I’m on sabbatical for the next three months and have committed to doing a literature review on neurodiversity and PhD study. Ugh. I hate doing literature reviews. I’m just going to say it: most academic writing is BORING and doing a big review means reading lots of it. The thought of reading more than 200 papers in 3 months makes me want to poke my eyes out with a pen.
The good news is I can use ChatGPT to help me write this review. There’s something of a moral panic around ChatGPT, or, as my twin sister amusingly calls it: ‘ChattieG’. We’ve heard much about the perils of misinformation and how to stop students cheating. While there are legitimate concerns about ChattieG around privacy, pollution and worker exploitation, I think a lot of the commentary misses the point.
Look, here’s my hot take, for what it’s worth: academics have a responsibility to show others, including our students, how to use these tools responsibly, creatively and ethically. Feeling conflicted about using the technology is reasonable because there is no ethical consumption under late stage billionaire-ist capitalism. While we should continue to critique how this technology is made and used, refusing to engage is not really an option. The genie is well and truly out of the bottle and the robots really will take our jobs if we don’t put ourselves in charge of this technology.
Ok, I will get off my high horse now.
It took me quite some time to work out how to make ChattieG genuinely useful. The rest of this post will document what I have learned so far, but check with your uni before you follow my lead. Here’s the advice from ANU, which is kind of vague and allows for exploration, unlike some others.
Generally, the best way to use ChattieG is to imagine it as a talented, but easily misled, intern/research assistant who has a sad tendency to be sexist, racist and other kinds of ‘isms’.
Instruct it like you would a human being with these shortcomings and you will get much better results. And I know this sounds weird, but it also helps give ChattieG an actual face. I typed in ‘cute, smart intern wearing glasses’ into AI image generator DALLE, and this is what I got:
Of course, ‘cute and smart’ means young white guy (sigh). But I suppose the image is a good reminder of the bias that seems horribly built into AI tools of all stripes. Ok, to the literature review – how can it help?
You can ask ChattieG to suggest ideas. While ChattieG can be a bullshit fountain, the bigger problem is its ideas are likely to be boringly pedestrian. Boring is not all bad: it can be a starting point for fact checking or to engage in some myth busting.
Let’s see how it does with my basic project idea, which is to help supervisors and universities better support neurodiverse doctoral students:
Prompt: I’m writing a literature review about neurodiversity in doctoral education. Can you list ten things that educators should know about neurodiversity when supervising doctoral students? Please touch on aspects of neurodiversity that can affect how people write, process information, approach deadlines and communicate with others. include a short description with each list item, written in academic style.
Response: Certainly, here are ten key things that educators should know about neurodiversity when supervising doctoral students:
- Neurodiversity refers to the natural variation in how human brains process information and perceive the world around us. This includes individuals with conditions such as ADHD, autism spectrum disorder, dyslexia, and other learning differences.
- Neurodivergent individuals often have unique strengths and abilities that can be leveraged to their advantage in academic settings. For example, some individuals with ADHD have been shown to be highly creative and innovative problem-solvers.
- Neurodivergent individuals may face challenges with executive functioning, which can affect their ability to plan, prioritize, and meet deadlines. Educators should be aware of this and work with students to provide support and accommodations as needed.
- Many neurodivergent individuals have different communication styles and may struggle with social interactions. Educators should be patient, flexible, and willing to adapt their communication strategies to meet the needs of their students.
- Neurodivergent individuals may process information differently than their peers, which can impact their ability to write and articulate their ideas clearly. Educators should work with students to identify strategies for organizing and expressing their thoughts effectively.
- Neurodivergent individuals may benefit from alternative forms of assessment, such as presentations or projects, that allow them to showcase their strengths in non-traditional ways.
- Educators should be aware of the potential for bias and discrimination against neurodivergent individuals in academic settings. They should work to create a welcoming and inclusive environment that celebrates neurodiversity and values diverse perspectives.
- Accommodations such as extended deadlines, quiet study spaces, and assistive technology can make a significant difference for neurodivergent students. Educators should work with students to identify and implement these accommodations as needed.
- It is important for educators to recognize the intersectionality of neurodiversity with other identities such as race, gender, and sexuality. They should be aware of how these factors can impact the experiences of neurodivergent individuals in academic settings.
- Educators should prioritize self-education and ongoing professional development around neurodiversity to ensure that they are providing the best possible support for their students. This may involve attending trainings or workshops, consulting with experts in the field, or engaging in ongoing research and reading.
That’s… not bad. There’s some good ideas here for me to follow up. I particularly like the one on intersectionality, which prompted me to widen my search terms in useful ways.
Use ChattieG to make tiny summaries of key concepts
An important part of note taking is putting other people’s concepts and ideas in your own words. ChattieG can do this for you by simplifying other people’s writing; translating the academic concepts and making them easier to understand. I use this feature to make tiny summaries of interesting ideas from papers I’m reading.
If the text you want to simplify is on the web, you can just point Chattie at the URL and it will do the whole document. But I prefer to use this feature on smaller chunks of text as you get more accurate results. Here’s a bit of text from a paper I found after taking ChattieG’s advice to explore intersectionality: “The Theory Of Intersectionality: A New Lens For Understanding The Barriers Faced By Autistic Women.” by Amanda Saxe published in Canadian Journal of Disability Studies in 2017. I understand these concepts, but the writing is very dense:
“Intersectionality takes into account that “identities are …culturally mediated constructs implicated in relations of power, privilege and oppression” (Liasidou, 2013, p.300). This is directly relevant to the social model of disability, conceptualized by Oliver (1983) in Social Work with Disabled People which proposes that disabilities are the result of societal barriers, rather than inherent deficiencies in the ‘disabled’ person (see also Appleby, 1994; Ballan, 2008; Hirschmann, 2012; Oliver, 1983). Individuals with disabilities face barriers constructed within the able-bodied communities in which they live (Ballan, 2008; Hirschmann, 2012; Oliver, 1983). They could lead ‘normal’ lives should these barriers (both physical and social) be removed, since it is these barriers that disable them (Hirschmann, 2012). Throughout history, Autism has been seen through a medicalized lens, where individuals with the disorder were viewed as deficient and abnormal (Bumiller, 2008). The neurodiversity movement has since emerged through the work of Autistic self-advocates, promoting the argument that Autism is the result of a difference in neurology which should be accepted as a form of human diversity”
Let’s see how ChattieG goes simplifying the key concept in this paragraph. You could just say ‘summarise’ and give it the text, but remember it’s better to talk to it like a research assistant. Tell Chattie what the source paper is about as well as reading level and style of output. I find instructing it to simply to a 9th grader level in academic style gives consistently good results:
Prompt: I’m going to give you some text from an academic paper about intersectionality and autism. Can you please produce a simplified version of this text. Make it to a 9th grader level, still in academic style: [text inserted here in quotation marks]
Response: Intersectionality is a way of looking at how different parts of a person’s identity, like their gender, race, and disability, can affect how they’re treated. People with disabilities have faced barriers to living a “normal” life because society isn’t set up to accommodate their needs. This idea is called the social model of disability. It says that disabilities are not caused by something that’s wrong with the person, but by the way society is set up. In the past, autism was thought of as a problem that needed to be fixed. But now, people with autism are saying that it’s just a different way of thinking and that this should be celebrated as a form of human diversity.
An important part of the note taking process is what I call ‘rambling’ – just typing out my thoughts for an audience of one: me. Rambling is a way of getting ideas out of my head and onto the screen so I can assess whether they are any good. Chattie is brilliant for taking these rambles and turning them into something… less shit.
Prompt: I’m going to give you some of my rough notes about how neurotypicals process information compared to people with ADHD. Can you rewrite these notes as the discussion section of a paper about the differences between how people with ADHD work, vs people with neurotypical functioning: “I’m going to give you my rough notes on what it’s like to work with ADHD. Can you turn these notes into an introduction to an academic paper? “I list each segment of the event in a table and then write the tasks associated with each part of the event. As I do this, I must imagine – literally walk through each part of the event in my mind. This is DMN in action, then I flip back to TPN to put the task into words on a page. Then I must imagine a future flow of work where I can do these tasks – which one needs to be done before the other, are there dependencies? I then flip to my diary and look at the work that is coming up – are there any ‘big rocks’ that are going to get in the way? Can I schedule this work or must I delegate it. I then have to imagine my co-worker’s flow of work and tasks. I have to imagine the physicality of doing something like a stocktake of our tea and coffee supplies and how that might fit into her schedule, which I see visualised in the team diary. When I look at my work this way I wonder how I EVER get things done. And yet I do. For me, this work is effortful, but not difficult. But to a person with ADHD with the faulty switch between these different cognitive processes, it’s really difficult. They can get ‘stuck’ in the past, not the future – remembering a previous event rather than imagining a future one. If something went wrong on that previous event, they may get stuck in rumination about it. Although they want to get on with their task list, it’s a conscious thing to try and switch out of DMN and back into TPN.”
Attention Deficit Hyperactivity Disorder (ADHD) is a neurodevelopmental disorder characterized by difficulties in executive functioning, attention, and working memory. Individuals with ADHD often experience challenges in organizing and completing tasks, particularly in complex work environments. This section will discuss some of the differences between how individuals with ADHD process information compared to neurotypical individuals and the implications of these differences for work activities.
One notable difference is the way individuals with ADHD break down complex tasks. As noted in the introduction, individuals with ADHD may engage in a cognitive process that involves breaking down events into smaller parts and imagining each segment in detail in their mind. This process requires them to switch back and forth between two cognitive networks, the default mode network (DMN) and the task-positive network (TPN). Neurotypical individuals may not engage in this process to the same extent, relying more on internal scripts and past experiences to guide their actions.
Another difference is the way individuals with ADHD handle distractions. Neurotypical individuals may be better able to filter out irrelevant information and focus on the task at hand. In contrast, individuals with ADHD may struggle to ignore distractions, leading to difficulties in sustaining attention and completing tasks.
These differences in cognitive processing can have significant implications for work activities. For example, individuals with ADHD may benefit from accommodations such as breaking tasks into smaller steps, providing regular feedback, and reducing distractions in the work environment. Additionally, it may be helpful to provide training on time management and organizational skills, as well as access to assistive technologies that can support executive functioning.
In conclusion, individuals with ADHD may process information differently compared to neurotypical individuals, particularly in terms of breaking down complex tasks and handling distractions. By understanding these differences and providing appropriate support, employers can create a more inclusive and productive work environment for individuals with ADHD. Future research can build on this work by exploring additional strategies for supporting individuals with ADHD in the workplace and evaluating the effectiveness of current accommodations and interventions.
Look, it got some of that wrong, but it’s easy to correct and not terrible. Now, here’s a neat trick my sister Anitra (who is a power ChattieG user) taught me, which you can have for free. When you have some of your rambling translated into prose, tell Chattie to keep making stuff up and see what happens. Some of it will be terrible, but it’s worth seeing where it will go with the ideas.
It’s a simple one word command this time:
Response: Further research could also investigate the role of cognitive processing in other areas of work, such as decision-making, creativity, and problem-solving. While individuals with ADHD may experience challenges in some aspects of cognitive processing, they may also demonstrate strengths in other areas, such as divergent thinking and innovation.
It is also important to note that not all individuals with ADHD will experience the same challenges or strengths in the workplace. The impact of ADHD on work performance may depend on various factors, such as the severity of symptoms, the type of work involved, and the individual’s coping strategies and support systems.
Finally, this discussion highlights the need for greater awareness and understanding of ADHD in the workplace and society at large. By promoting education and awareness about ADHD, we can reduce stigma and misunderstandings and create a more supportive and inclusive environment for individuals with ADHD and other neurodivergent traits.
In conclusion, this discussion highlights some of the differences between how individuals with ADHD process information compared to neurotypical individuals and the implications of these differences for work activities. By understanding and addressing these differences, employers can create a more inclusive and productive work environment for individuals with ADHD.
Similarly to the initial brainstorming, Chattie is largely giving me banal ideas, but I like the point it makes about difference in the first paragraph.
Again, I wouldn’t use this text exactly as its given – for me, this is part of a creative process towards a first draft. I’ll end up rewriting this text completely I suspect, but ChattieG definitely reduced some of the cognitive ‘heavy lifting’.
I suspect people will have Feelpinions about using ChattieG this way… as My friend Dr Jason Downs pointed out to me in one of our podcasts: academics have been trained not to accept help with thinking work.
We award PhDs in recognition that people are capable of independent thought and knowledge making. Using a machine to help generate ideas feels… weird and wrong. Mind you, I would have no problem if the ideas were a result of a conversation with other humans. Is using ChattieG to continue a thought ‘cheating’, or leveraging a technology to extend thinking in a way that was previously not possible? I’m still trying to work that one out.
Use ChattieG to improve your existing prose.
I love Grammarly for cleaning up text, but it feels like a lot of work compared to cleaning text with ChattieG. In our book ‘How to fix your academic writing trouble‘, Katherine, Shaun and I discuss how to use insights from linguistics to help make prose sound more ‘academic’. Here’s some prompts I wrote, using our book, to automagically apply some of these principles to your prose:
- Rewrite this text with less nominalised verbs [or, rewrite with more nominalised verbs]: [insert text]
- Rewrite and reduce instances of the following words: Is, Am, Are, Was, Were, Be, Being, Been and the word ‘that’: [insert text]
- Rewrite this paragraph, introducing more bridging sentences to increase clarity [insert text]
- In the following sentence, please identify the theme and the rheme: [insert sentence]. Follow up prompt: Rewrite the previous sentence to make the connection between the theme and rheme clearer.
- Please provide me with a list of conjunctive phrases to link ideas that have a [particular kind of logical relationship, eg ‘cause and effect’, ‘comparison’, ‘contrast’] relationship.
I’ve been mucking around automating my note taking in other ways by plugging ChattieG into Obsidian with the TextGenerator and SmartConnections (thanks Peter Hayes!), but that’s a post for another time. I have topped 3000 words already!
In case you are wondering, while I am here in the UK on sabbatical I’m attached to Think Lab in Cambridge, where I will do some workshops. I will also be getting around the UK a bit. I’ve confirmed visits to the universities of Glasgow, Ulster, Warwick, Nottingham, Manchester, Gloucestershire and Bristol – and yet to confirm Oxford, but hope to very soon. I’ll be releasing details of any public lectures and workshops on my Thesiswhisperer LinkedIn page, where you can also respond to this post.
Before I go though, here’s my sabbatical writing view at home, while I am in Cambridge:
I’m so honoured to be staying in the house of the late Professor Adam Kendon while I am in the UK on sabbatical. I read (and cited) so much of Dr Kendon’s ground breaking work on hand gestures when I did my own PhD thesis nearly 20 years ago. I wrote to Dr Kendon after I finished my PhD and remember his generosity and kindness to me, as a young, nervous scholar. His example of collegiality has long stood out as a model for me. His personal library here is astonishing and it’s honestly the experience of a lifetime to be sitting and writing this at the desk of one of my academic heroes. Big thanks to the Kendon family for lending Mr Thesiswhisperer and I this beautiful house.
Now that Twitter has been ‘Elonified’, the best way to follow Thesiswhisperer on the socials is via my Thesiswhisperer LinkedIn page. I drop all new posts and pods there first and it’s a good place to talk to me and ask questions.
This month’s podding:
- How to get to inbox zero and other stories (includes a lot of me talking about using ChattieG too)
- Severance pod is about to drop! You can follow and subscribe here.
You can also listen to the teaser trailer of Academics talk about Severance. The pod will drop over April and May
Building a second brain for writing – with Obsidian
Are the robots coming for our (research) jobs?
I wrote Be Visible or Vanish with Simon Clews to help all researchers present their research, inside or outside the academy. You can pre-order now on all good book sites, or via Routledge here.
Here’s the blurb:
The world of the academic researcher is changing; it used to be enough to work hard, do your research and get your results published. Not so these days. Universities now expect researchers to share their work with the world, as widely as possible. ‘Publish or perish’ has been replaced by a new mantra, and the pressure is on.
In this insightful book, Inger Mewburn and Simon Clews look at some of the most common presentation scenarios that researchers will face when talking about their work. Starting in academia with the deceptively simple art of writing a good email and working through lectures, conference presentations and lightning talks, the book then moves ‘off campus’ and explores talking to the media, making elevator pitches and creating an effective digital presence on social media.
Offering detailed looks at 19 different presentation formats, Mewburn and Clews tap into their vast experience in the field to analyse the challenges and opportunities aligned with each case study and to map out the route to success. With a lightness of touch and an often humorous approach, Be Visible Or Vanish: Engage, Influence and Ensure Your Research Has Impact will show you what it takes to achieve that holy grail of modern academia… impact.
This text will be invaluable for students, academics and researchers hoping to effectively communicate complex information in a way that can be understood and appreciated by their peers, colleagues and the wider world.
Love the ThesisWhisperer?
I cover all the expenses of operating the Thesis Whisperer out of my own pocket. If you enjoyed this post and want to support the work, you can buy me a virtual coffee here or consider becoming a $1 a month Patreon
Alternatively, consider buying a copy of one of my ebooks directly from this site:
Tame your PhD
The Year of Living Covidly
TextExpander for Academics
I’ve authored, co-authored or been involved with eight books now – you can find them all on the Buy Books page. Thanks in advance for the support!