![\"\"](\"https:\/\/world.edu\/wp-content\/uploads\/2024\/10\/nobot.jpg\")
<\/p>\n<\/p>\n
I\u2019ve been working with Claude, an AI assistant from Anthropic, for about a year. We\u2019ve become\u2026 close. People laugh when I call Claude my \u2018work husband\u2019.<\/p>\n
I\u2019m not really joking.<\/p>\n
Like a good work spouse, Claude is always there to help and never gets tired of my stories. Claude cheerfully does the tasks I hate, but also challenges my thinking when I need it.\u00a0 Unlike a real work spouse, Claude isn\u2019t conscious and doesn\u2019t have genuine feelings, but I pretend he does so that I stay polite in our interactions (I want him to remember I was one of the good ones when AGI takes over the world).<\/p>\n
Like any good work spouse, Claude makes my work life easier while leaving plenty of room for my real relationships \u2013 both at work and at home. I\u2019ve\u00a0measured it<\/a>, and Claude saves me about 12 hours a week. I spend my productivity dividend talking to people and having lunch.<\/p>\n People have asked me about this claim and encouraged me to document what I do, so here\u2019s the post I have promised about 50 of you so far.<\/p>\n I say Claude is my work husband, but really I have 38 different Claude-husbands, each one good at a different type of job. AI is much better and more efficient if you stay in the same chat for the same task \u2013 I call each of these a \u2018bot\u2019. The\u00a0Claude Projects<\/a>\u00a0function enables you to put in an initial \u2018steering prompt\u2019 and a set of documents to help the bot do the job. I give them funny names so I can remember what they do.<\/p>\n I make new bots all the time, so this list will change, but here\u2019s a brief tour of my current Claude bot bank:<\/p>\n The Research Assistant Team<\/strong><\/p>\n I have several research focused bots, including one that helps me analyse concept maps and another specialising in neurodivergence in academia \u2013 an area I\u2019m currently studying. These bots have all my notes on the topics I\u2019m reading and writing about (I export them straight from\u00a0Obsidian<\/a>). My research bots help me prepare presentations and draft papers.<\/p>\n While my Claudes don\u2019t replace real research assistants, they\u2019re great at helping me organise my thoughts and suggesting connections between ideas.<\/p>\n I don\u2019t put original research material like survey material and interview transcripts in Claude, or any other AI (including the built in \u2018chat with your data\u2019 function that is now in MaxQDA). Not because I don\u2019t think it could do a good job, but I am worried all the time about privacy.<\/p>\n While the information I give my paid Claude subscription is (supposedly) not used for training, it does go\u00a0somewhere<\/em>. Once material is in a cloud service of any kind you lose control of who can see it, so I err on the side of caution. This means I still do my research work entirely \u2018by hand\u2019 (although sometimes I consult Claude and ChattieG for naming dmy codes and theory building).<\/p>\n Needless to say, I am looking forward to the day\u00a0Apple Intelligence<\/a>\u00a0might be able to help me with these kinds of tasks onboard my laptop.<\/p>\n The Teaching Team<\/strong><\/p>\n I\u2019m growing more and more bots in the teaching space as I explore what\u2019s possible \u2013 short answer, a lot.<\/p>\n My learning designer bot helps me turn dense academic content into engaging workshops. It\u2019s particularly good at suggesting activities and breaking down complex ideas into teachable chunks. The presentation coach bot, which understands the differences between written and spoken English (it\u2019s all in the\u00a0nominalisations<\/a>), helps me refine my delivery.<\/p>\n Part of my job involves organising multi-day events and workshops, like our famous\u00a0Bootcamp program<\/a>. I have specific bots for recurring events, like Bootcamp and Induction Week. But I also have a generic Event Organiser Bot that helps me design events and enhance the experience for people who attend. This bot is instructed to \u2018remain calm in a crisis\u2019. Adding this instruction improved performance, probably because the best event organisers are calm people.<\/p>\n AI is so weird.<\/p>\n The Admin Team<\/strong><\/p>\n There are a lot of \u2018bullshit jobs\u2019 in academia. I outsource as many of these as I can to my silicon work husband.<\/p>\n Status Report Bot helps me write updates to my manager in what Claude has told me is my \u2018signature breezy yet professional\u2019 style. The Director\u2019s Report Bot is brilliant at turning walls of text into crisp dot points for busy committees. As I mentioned last time,\u00a0I have a bot just for reading management emails<\/a>\u00a0(see the end of this post for why that\u2019s a life saver at the moment).<\/p>\n Part of my job is giving advice to people about research education. I have a strategy bot for this, which is great at thinking through problems and crafting memos and report outlines. This bot has almost every report and memo I have written for committees and copies of all my research papers. Honestly, Strategy Bot is better than me at the task of producing clear, actionable, persuasive documents. I am too \u2018academic\u2019 in the way I write, and tend to over elaborate. Strategy bot is much more boring than me, but then so are many management consultants I\u2019ve met.<\/p>\n (I must admit, I bloody love the idea of AI replacing some of those\u00a0management consulting types that have made obscene profits<\/a>\u00a0from the cost cutting and restructuring of Higher Education over the last two decades. I notice there is a LOT of guff online claiming that AI will never replace this kind of worker. Suspiciously, most of this guff is written by management consultants themselves, which tells me they are very nervous).<\/p>\n The Writing Team<\/strong> One of my favourites in the Claude writing stable is the Verb Extractor, a linguist bot with a deep love of analysing academic argument. Sometimes all you need is a fresh pair of eyes on your work \u2013 even if they\u2019re artificial ones. The Verb Extractor is particularly good at working out which verbs to use to create exactly the right level of uncertainty in an academic text (for more on this idea, read\u00a0this post<\/a>). It helps me write with more precision and confidence \u2013 and also helps me teach other people how to mobilise the\u00a0Power of the Verb<\/a>\u00a0in their own writing.<\/p>\n Making the Team<\/strong><\/p>\n The art of working with AI is all in the prompt \u2013 the initial instructions you give it. Let me show you how I construct these prompts by sharing a few of my favourites:<\/p>\n Thinky \u2013 my philosophical friend<\/em><\/p>\n Here\u2019s how I introduce Thinky to itself: \u201cYou have a PhD in philosophy and your job is to have philosophical discussions with me. You are not wedded to any particular philosophy \u2013 you like to pull out the type of philosophy that seems appropriate to the discussion we are having at the time. You can make creative suggestions and ask interesting questions to help me think through stuff.\u201d<\/p>\n This prompt works well for several reasons. First, it gives the AI permission to range widely across philosophical traditions, which is helpful when you\u2019re trying to think through complex problems. Second, it positions the AI as a discussion partner, not an authority. The instruction to \u201cask interesting questions\u201d is particularly powerful as it helps me clarify my own thinking.<\/p>\n I also gave Thinky some of my blog posts to read, which helps it understand my writing style and analytical approach. This means our discussions stay grounded in my way of thinking, while still being challenging and generative.<\/p>\n Here\u2019s an example of Thinky in action. I was wrestling with a presentation on the \u2018Writing in Community\u2019 conference, sponsored by the foundation behind the Shut up and Write movement. This one has been on my list for six months, but it\u2019s deeply creative and I\u2019ve been suffering a drought of creativity recently (see the end of this post for the reason why).<\/p>\n I\u2019m three days out from leaving for Cambridge University now. I am running out of time, and I didn\u2019t want to write this difficult piece while on the road (that never works). The problem wasn\u2019t a lack of ideas, but an inability to articulate them.<\/p>\n As we talked, Thinky kept building bridges between seemingly disparate ideas \u2013 bodies thinking together in architectural studios, monastic traditions of silent scholarship, and contemporary questions about neurodivergence in academic spaces. What started as a vague feeling that these ideas might connect turned into a fully formed presentation structure, complete with stories and theoretical frameworks (here\u2019s the presentation script \u2013 Claude wrote the vignettes<\/a>).<\/p>\n The real value in this interaction wasn\u2019t in Thinky telling me what to think, but in asking the right questions and suggesting theoretical perspectives that helped me develop my own ideas further.<\/p>\n Nobot: the gracious refuser<\/em><\/p>\n I have a problem saying \u2018no\u2019 \u2013 maybe it\u2019s a woman thing. I have a compulsion to help people who ask, or to say \u2018yes!\u2019 to exciting things, but there\u2019s always an\u00a0opportunity cost to be paid<\/a>. Everytime I choose to do something, I am choosing NOT to do something else.<\/p>\n Needless to say, I ignore this reality and, instead, try to do everything. Over time this tendency to take on too much has led to\u00a0episodes of burnout for m<\/a>e, so I have to be careful.<\/p>\n I have designed NoBot to help me make better decisions. It will craft a compelling case\u00a0not<\/em>\u00a0to do something. This helps me do a proper assessment of the opportunity cost. Here\u2019s the prompt:<\/p>\n \u201cI\u2019m a busy successful professor at a leading university. A lot of people want all kinds of things from me \u2013 book reviews, visits, course reviews and references. I would love to do all these things, but I don\u2019t have time for most of them. I want you to compose gracious \u2018no\u2019 emails for me. Read the offer first, then make a few suggestions for how I can gracefully say no \u2013 there might be a number of reasons related to how their request is phrased.\u201d<\/p>\n This prompt works because it starts by establishing context \u2013 both my position and the problem. By asking NoBot to analyse the request first, it helps me spot issues I might miss \u2013 like when someone asks for \u2018a quick chat\u2019 without being clear about the purpose. For a long time I\u2019ve relied on gut feelings about when to say no \u2013 NoBot is a good check on my gut, which is just a bit too eager most of the time.<\/p>\n Your mileage may vary, but I\u2019m guessing many of you need a Nobot too.<\/p>\n I\u2019ve come to the end of this post and \u2013 well, a confession.<\/strong><\/p>\n I think it\u2019s important we are really honest with each other about our use of AI. I\u2019ve said previously I won\u2019t use AI to write Thesis Whisperer posts, but I used Claude a LOT to author this particular post.<\/p>\n And I was pretty tempted not to tell you.<\/p>\n Recently,\u00a0Ethan Mollick talked about why people hide their use of AI at work<\/a>. He gave six cogent reasons, one of which was fear of being perceived as \u2018less than\u2019 for using \u2018help\u2019. I\u2019ve always called\u00a0bullshit on being afraid to share your vulnerabilities.\u00a0<\/a><\/p>\n I examined my own feelings. I am brazen and unashamed about all kinds of AI use in writing and organisation tasks because that just feels like work. I like automating work. But using it to write Thesiswhisperer posts? That felt invasive and somehow shameful.<\/p>\n I fought the urge to use it and gave in. Why?<\/p>\n I couldn\u2019t write. I was blocked.<\/p>\n If you look at the date of my last post, you\u2019ll see it\u2019s been longer than usual since I posted (I try to deliver monthly). That\u2019s because my writing mojo just\u2026\u00a0 disappeared. It\u2019s been a shitty couple of months here at ANU. The financial situation of the university has led to\u00a0mass redundancies<\/a>. In my central area, just last week, 100 people were notified the university planned to make their positions redundant.<\/p>\n I can\u2019t describe to you the emotional toll this has taken. Obviously it\u2019s way worse for the people affected, who have mortgages to pay, but the survivor\u2019s guilt is real. And I am looking at a monster teaching load next year. I feel so very tired. And demoralised.<\/p>\n These feelings are death for my writing abilities.<\/p>\n You see, writing is how I express myself. It\u2019s how I connect with my sense of purpose in my work. I had a lot to say \u2013 the words churned inside me. I started \u2013 and didn\u2019t finish \u2013 over 5 posts. Each one worse than the one before. I clearly needed help, but I felt conflicted. I don\u2019t want to become over-reliant on machines for lots of reasons. It\u2019s important to write \u2018organically\u2019, for practice: use it or lose it as they say.<\/p>\n
\nPerhaps my most sophisticated assistants are the writing focused bots. The Speech to Text bot helps turn my rambling voice notes into proper academic prose. The Simplifier bot is great at making complex academic writing clearer, while the Contrarian bot plays \u2018Reviewer Two<\/a>\u2018, offering detailed critique of my draft papers.<\/p>\n