ERP Therapy Sucks

I have OCD (or had?) I did a course of ERP with a very good therapist who I would put as the most important person in my life after my partner and family even though I hope to never need to speak to her again. It was a life changing experience in that my average day-to-day quality of life went from something like a 2/10 to a 9/10. I frequently fantasised about killing myself. At least once a day, from ages 12-32. Though I thankfully never went as far as to make concrete plans.

With that context, I can't see a way in which ERP therapy with an LLM (at least, the consumer system prompts we are used to and often think of) would not backfire and be actively harmful.

There are two reasons, and both relate to the people-pleasing tuning that ChatGPT etc have:

1. ERP is actively uncomfortable, that is the point. But there is a delicate balance to the level of discomfort.

Too comfortable and you make no progress. Too uncomfortable and you can set yourself back enormously. We aren't talking one step forward and two back. I got overly confident two months in and put myself in a worse state than I had been on entering therapy (though not my worst state overall over the 20 years). I haven't seen many people in support groups do very successful self-administration of ERP for this reason. My therapist had to do a lot of non-verbal reading of my reaction to gauge if I was at an appropriate level of discomfort, as it was not something I was able to verbalise myself without a lot of practice and learning - and that learning and practice came from guidance by a human who didn't need me to be able to articulate it already.

2. Reassurance seeking is a compulsion, and it is one of the most common and difficult to stamp out.

I can't see an LLM not providing reassurance when asked for it, and so I can't see anyone using an LLM for therapy as making any progress at all without a level of discipline and awareness they would have had to obtain from in person ERP anyway.

> Luckily, LLMs significantly reduce the effort/cost of therapy experiments.

The day just started and I'm already done with it.

I have had clinical OCD for decades. It becomes part of the brains default mode network (DMN) and flares up for me when frazzled, stressed or neglecting health. I’ve learned to cope, know why it happens, that it’s harmless and it’s faded with age. I recommend extreme physical exercise that burns off the associated anxious adrenaline and “reminds” the body what relaxed feels like while knocking loose stuck attention. You simply can’t focus on much else when your legs are burning huffing and puffing. There are great benefits of activating the parasympathetic nervous system, releasing natural endocannabanoids and endorphins, experiencing muscle soreness to help you feel grounded and most of all “exercising” the attention system. In time the DMN ruminations will go down exercise causes known changes to brain blood flow, activating different regions, and promoting nueroplasticity/rewiring is part of that. Get sleep to keep from getting frazzled and eat healthfully (actual nutrition, hire someone). Human-generated content may contain personal bias O_O

I like how the author says that they only started a few weeks ago and (contrary to the title) find it good, actually, but has already amassed the requisite expertise to advise other people not to seek out therapy from human beings if they don’t get the result they want from a chat bot.

It is literally “My Mental Health is Improving Through Human Contact: Human Contact Might Not Be For You. The Only Way To Know Is By Asking The Computer”

It is kind of like “I started exercising with a trainer and I feel better and I’m losing weight, because of this I suggest you take up smoking and based on that decide whether or not you want to exercise”. Like the advice is simultaneously almost completely unrelated to their experience and also the exact opposite of their experience.

I cannot wait to hear more well-thought-out advice from the author of “God created men; Sam Altman made them equal”

There’s a coaching diagram which goes like this:

- I want to do a thing.

- Do the thing.

- but I’m scared

- Do it scared.

I've got OCD and I've done CBT, ERP etc. As others have alluded to, you need to realise the work is never done. Recently I've found it more active, but this time - having recently read The Maps we Carry by Rose Cartwright, who was something of a poster-woman for OCD after her first book, Pure - I've tried to go deeper. CBT etc feel like prophylactics. They're certainly useful, but they don't address deeper things, such as learning to be as you are, to observe and integrate your anxiety etc.

This set me off on a harder path of more abstract therapy (I'm working with an integrative therapist who practices across IFS, Jungian etc), meditation etc. The book the untethered soul, by Michael Singer helped a lot to put everything into perspective - the therapy, the anxiety, the day to day - in a way that nothing else had really achieved for me.

Also, a key conclusion of Cartwrights is that individualised change/treatment is important, but it's worthless without community. I think she's deeply, profoundly right.

Author here! Thanks for all the feedback on my LLM tangent, quoted here for posterity:

  Luckily, LLMs significantly reduce the effort/cost of therapy experiments. Consider trying the following prompt:

  > Please guide me through a round of ERP therapy. Start by listing universal sources of fear/discomfort/anxiety.

  If you find this process useful, consider trying it with a licensed human professional.

After some consideration, I agree that this advice could backfire for some people. I removed it from the essay.

Do you know of any low-friction ways to systematically tackle fears/discomforts? I really want to recommend a quick experiment that folks can try at home without doing full-blown therapy.

If you're interested in this topic, I very warmly recommend the book You're not a rock by Mark Freeman. There are also episodes of podcasts around with interesting interventions from him.

The way I usually pitch the book is that Mark is not an MD, or a scientific expert on the topic, but he is a patient who's been through it, is very interested, and explains to you how it worked for him, and what he knows about the topic like a friend would. There are some mistakes, some things are a bit awkwardly explain, but the book is overall a tremendous read for anyone interested in anything dealing with anxiety, ocd, or more generally a mind too keen on spinning in a wheel.

https://www.markfreeman.ca/books/

OCD can be harsh, and immune to a lot of approaches. It might feel like "LLM on a low temperature".

Even in "Realms of the Human Unconscious: Observations from LSD Research Paperback" by Stanislav Grof, OCD gives remarkable resistance not only to therapy, but even to psychedelics. This book discusses a case of a person with OCD who took 500ug of LSD (well, a rather high dose) yet neither the patient nor their psychiatrist noted any effect. Yet, after getting at ease, much smaller dose worked (and there was a remarkable progress).

What might work though, is reducing overall stress revel. OCD symptoms are often a response to anxiety and uncertainty.

The off center content, the jarring contrast between the background and the image, the padding at the bottom, the changing of the cursor to a very similar, yet different one... The page is clearly coherent, I don't meant to imply the author doesn't know design, but it's as if every bit was meant to annoy me slightly. It's almost impressive.

Another vote here against using LLM. Because if you do ERP incorrectly then you can even worsen the fear and make your life even harder.

Example:

You are afraid of dogs. LLM tells you to approach one to habituate your anxiety. You do that but the fear overwhelms you and you run away.

Brain’s diary: I avoided death, that beast would shred me to pieces in a moment.

(Note this is about „normal” anxiety and not OCD, but the idea translates.)

If you dont want (or e.g. cannot afford) a proper therapy, IMHO a book by a competent author is a much better choice than LLM. Or a few different books.

Only tangentially related, but maybe helpful still: If you struggle with OCD, the books by Sally Winston and Martin Seif are pure gold. There's nothing that helped me finding a way to deal with OCD like they did.

Minimised? Yes. But I’ve never seen a cured case of OCD, of any type.

I was with it right down to near the bottom where the author suggests people try it out using an LLM. Hmm, LLMs fall for cargo cults and I'm not sure they are to be trusted with even the most trivial self-help.

Author shoots the article in the head instantly with the suggestion that LLMs have a part to play.

Erotic Roleplay?

ai, I bet its got a conscious mind too!!!!!!

CBT/ERP, medicalised Skinner pavlovian model, cheap, short term relief of symptoms, no long lasting effect.

CBT = there is no unconscious!

CBT is based on a theory that it is not events in themselves that upset us, but the meanings we give them. However, CBT believes that this meaning is conscious, can be accessed, and is not ambiguous.

If someone says that they feel sorry for a person, they do feel sorry and it is possible that their problem is that they should not; the therapist then tries to help the patient to see that they are thinking about something in the ‘wrong way’. By using brain washing techniques.

The concept of the unconscious, a central Freudian discovery, renders the picture instantly more complex: if you say you are sorry for someone it might indeed mean that you are sorry, but could also mean that you can’t face your own aggressiveness and the fact that you are delighted at what happened to the other.

The question of the existence of the unconscious is crucial, because if CBT starts to take into account the possibility of unconscious meanings and logic, then it would become another branch of psychoanalysis.