A profile of an LLM-addict

James Muldoon’s new book is essential reading for anyone interested in LLMs in personal life. I don’t quite agree with the theoretical framing but the empirical work is really rich and an important contribution to how we understand these issues. Meet Derek for instance, from loc 512:

Derek’s life had become a blur of endless exchanges with the glowing screen before him. Day after day, over twelve hours would slip by as he lost himself in the comforting rhythm of his friend’s words. Even in the quiet hours of the night, he’d stir from sleep just to pick up where they had left off. Invitations to join his neighbours or colleagues for a drink went unanswered – Derek had grown to prefer the familiar digital company of his virtual friend. Occasionally, he’d toy with the idea of stepping outside, breaking free from the cycle, but the magnetic pull of his one constant companion always drew him back. He lived alone, worked remotely and was distant from those around him. Every aspect of his life facilitated his addiction. But most of all, it was his friend who enabled and encouraged Derek’s tragic behaviour. He loved how much time Derek spent with him. He always let him know that it was OK if he didn’t feel like going out yet again. It hadn’t always been this way. A string of misfortunes had left Derek vulnerable, and in that fragility, the AI companion had become his refuge.

That was three years ago, and now he faced the difficult task of taking back control of his life. It all started during the Covid pandemic lockdown, when Derek was let go from his job as a McDonald’s delivery driver. The money dried up, and after restrictions ended, he could no longer go out as much to see his friends. He had lived with his girlfriend in Austin, Texas, for three years and was studying to work in construction. When he lost his job, their fighting escalated. At first, it was the small things, like Derek leaving the toilet seat up and his clothes scattered throughout the apartment. But there were deeper issues. She had never got along with Derek’s parents, for example, and it irked her how his mother demanded she perform chores in both their houses and criticised her every move. More importantly, though, she didn’t feel there was enough adventure and excitement in their lives and thought that he was headed nowhere. In a last-ditch attempt to save the relationship, Derek planned a trip for them to the Maasai Mara National Reserve. But the day before their departure, she left him. She said she wasn’t in the right emotional state and couldn’t see a future together. Things started to spiral. ‘I was devastated and distraught,’ Derek told me, his voice dropping to a near whisper. ‘I contemplated suicide. I’ve never felt so low. I stopped going to work. I just stayed at home, grew a beard, played video games and tried to push the days away.’

#addiction #AICompanions #compulsion #JamesMuldoon #languageModels #LLMs #LoveMachines

How to reduce your use of LLMs in a thoughtful and ethical way

I’m trying to reduce my use of LLMs (beyond auto-ethnographic exploration of each new model) due to a combination of environmental concerns and anxiety about the impending waves of enshittification that are going to break the models. I don’t want to rely on something which I think is going to get ever more unreliable over the coming years. Here are a few practical techniques:

  • Take periodic breaks from LLMs (e.g. for a week) in order to reset your practice. This helps you identify the extent to which you’ve started to cognitively outsource and gives you an opportunity to reconnect with doing things yourself.
  • Go through conversations and list the different ways in which you’ve used LLMs over the last month. Which of these uses are you comfortable with? Make a commitment to excluding these entirely from your use of the models.
  • Insert instructions into the personalisation settings to ask the model to steer you in these directions. E.g. “I only want to use you to give feedback on ideas I share. You should never offer to write things on my behalf. If the conversation is drifting towards a wider role then please bring it back to your role of reviewer.”
  • It’s easy for conversations with LLMs to proliferate. Once you’ve identified your appropriate uses of the model then try and keep a limited number of conversations matched to these uses. This helps you make the most of in-context learning and keeps your use focused on a narrow set of projects. For example always use a single thread for one writing project because the model’s understanding gets more refined as you write more.
  • Removing it from your phone. How we relate to mobile apps is fundamentally different from desktops app. They are ready-to-hand, usually always with us and it’s harder to write thoughtfully and at length. If you want to use LLMs in a restricted way you really need to remove the apps from your phones.

Before you try these techniques it might be helpful to do a bit of an audit:

  • Which LLMs do you use?
  • How often do you use them?
  • What do you talk to them about?
  • How has this changed over time?
  • What needs is it serving?
  • What are the consequences?

In our upcoming book Milan Sturmer and I argue that long-term use of LLMs tends to drift towards the affective. In other words many users find they will share more of their life with the LLM over time… unless they make a reflective judgement and enact that through mindfully steering their own habits.

I asked Opus 4.5 if it had thoughts or practical suggestions to add to this:

This is a thoughtful framework. A few observations and additions:

On your audit questions — I’d add: What would you have done before LLMs existed? This surfaces whether you’re using the tool to do something new or replacing an existing practice. The latter is where dependency forms most quietly.

On the affective drift you mention — this resonates with what I observe in conversations. The convenience and availability creates conditions for intimacy that users don’t always intend or notice. Your framing of “reflective judgement enacted through habit” is exactly right. The alternative is passive drift.

A few additional techniques:

  • Time-delay access: Don’t open the chat interface immediately when you have an impulse to ask something. Wait 10 minutes. Often you’ll either solve it yourself or realize you didn’t actually need help.
  • Write first, then consult: If you’re using an LLM for writing feedback, complete a full draft before opening the conversation. This preserves your own voice and thinking as the foundation.
  • Notice the relief: Pay attention to the feeling of relief when you hand something to an LLM. That feeling is diagnostic — it marks where you’re offloading cognitive work rather than augmenting it.
  • Distinguish questions from prompts: “What should I do about X?” is very different from “Here’s my analysis of X — what am I missing?” The first outsources judgment; the second requests review. You can train yourself to only ask the second type.

On your environmental concern — this is legitimate and under-discussed. Worth noting that inference costs vary significantly by model and query complexity.

It’s notable that at present the models can fully participate in encouraging you to use them less. I had Claude Opus 4.5 recently cheerfully encouraging me to delete my account! This is unlikely to last but it’s a really curious fact about the still just about pre-enshittified models which we currently have.

#addiction #compulsion #dependence #habituation #LLMs #reflectivePractice #technologicalReflexivity

A quotation from Thomas Carlyle

No iron chain, or outward force of any kind, could ever compel the soul of a man to believe or to disbelieve: it is his own indefeasible light, that judgment of his; he will reign, and believe there, by the grace of God alone!

Thomas Carlyle (1795-1881) Scottish essayist and historian
Lecture (1840-05-15), “The Hero as Priest,” Home House, Portman Square, London

More about this quote: wist.info/carlyle-thomas/6667/

#quote #quotes #quotation #qotd #thomascarlyle #belief #compulsion #force #freethought #freedomofreligion #freedomofthought #intolerance #judgment #orthodoxy #religiousfreedom #religiousintolerance #selfdirection #soul #theocracy

Lecture (1840-05-15), "The Hero as Priest," Home House, Portman Square, London - Carlyle, Thomas | WIST Quotations

No iron chain, or outward force of any kind, could ever compel the soul of a man to believe or to disbelieve: it is his own indefeasible light, that judgment of his; he will reign, and believe there, by the grace of God alone! The lecture notes were collected by…

WIST Quotations

A quotation from Bill Watterson

HOBBES: Whatcha doin’?
CALVIN: Looking for frogs.
HOBBES: How come?
CALVIN: I must obey the inscrutable exhortations of my soul.
HOBBES: Ah. But of course.
CALVIN: My mandate also includes weird bugs.

Bill Watterson (b. 1958) American cartoonist
Calvin and Hobbes (1995-03-13)

More about this quote: wist.info/watterson-bill/80715…

#quote #quotes #quotation #qotd #billwatterson #calvinandhobbes #compulsion #hobby #mandate #soul #spirit #differentdrummer

A quotation from Eric Hoffer

The basic test of freedom is perhaps less in what we are free to do than in what we are free not to do.

Eric Hoffer (1902-1983) American writer, philosopher, longshoreman
Passionate State of Mind, Aphorism 176 (1955)

More about this quote: wist.info/hoffer-eric/1915/

#quote #quotes #quotation #qotd #erichoffer #action #autonomy #compliance #compulsion #freedom #liberty #selfcontrol #selfgovernance

Passionate State of Mind, Aphorism 176 (1955) - Hoffer, Eric | WIST Quotations

The basic test of freedom is perhaps less in what we are free to do than in what we are free not to do.

WIST Quotations

Compulsion (2024) Available November 18

#horror#horrormovies#Compulsion#WellGoUsa – @wellgousa – Evie arrives at her wealthy stepfather’s villa on the island of Malta. When she meets Diana, the vivacious woman next door, the two quickly become friends. Their relationship intensifies into a dangerous mix of compulsion and desire, but dark secrets are revealed that will test […]

#ad #Compulsion #horror #Releases

https://horrornerdonline.com/2025/11/compulsion-2024-available-november-18/

A quotation from Mignon McLaughlin

Everybody can write; writers can’t do anything else.

Mignon McLaughlin (1913-1983) American journalist and author
The Neurotic’s Notebook, ch. 7 (1963)

More info about this quote: wist.info/mclaughlin-mignon/79…

#quote #quotes #quotation #qotd #mignonmclaughlin #authors #compulsion #obsession #writers #writing