Live data from Hacker News

ERP Therapy Sucks

taylor.town

51–59 of 59 posts

Re: ERP Therapy Sucks

#51
post #2

> Luckily, LLMs significantly reduce the effort/cost of therapy experiments. The day just started and I'm already done with it.

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

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

What are you quoting? I don't see the sentence "Luckily, LLMs significantly reduce the effort/cost of therapy experiments," in the OP.

Re: ERP Therapy Sucks

#52

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…

If there's one thesis of this site it's that technology workers can trivially hack their way to expertise in any field they choose, using their intelligence and "curiosity" to bypass life experience, earned wisdom, and formal education. Analogous, I supppose, to how it's so easy for us to put up a web site in any new language in less than a weekend? It's abysmal.

Re: ERP Therapy Sucks

#53
post #2

> Luckily, LLMs significantly reduce the effort/cost of therapy experiments. The day just started and I'm already done with it.

>> Luckily, LLMs significantly reduce the effort/cost of therapy experiments. > The day just started and I'm already done with it. What are you quoting? I don't see the sentence "Luckily, LLMs significantly reduce the effort/cost of therapy experiments," in the OP.

The page has been updated; there was a whole bit about using LLMs to generate ERP prompts and feedback for self treatment. It was a complete clown car.

Re: ERP Therapy Sucks

#54
post #35

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…

I think it's more like "I started exercising with a trainer and then realized I don't actually need to be paying the trainer all that money, because the exercise was the important part".

It looks like the “just talk to a chat bot instead” part has been removed, so I’m now not sure what the author wanted us to take away from this post

Re: ERP Therapy Sucks

#55

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 consider…

>Do you know of any low-friction ways to systematically tackle fears/discomforts?

The same ways people did before 2022. Talking to friends and family or other community members, reading books by experts, joining support groups, attending seminars and workshops, or finding communities (of real people) online.

The only reason why chat bots are able to generate text that looks plausibly like good advice is that there was an enormous amount of publicly-available experiences and advice created by real people in the data that it was trained on.

Re: ERP Therapy Sucks

#57
post #35

Earlier quoted context omitted.

I think it's more like "I started exercising with a trainer and then realized I don't actually need to be paying the trainer all that money, because the exercise was the important part".

It looks like the “just talk to a chat bot instead” part has been removed, so I’m now not sure what the author wanted us to take away from this post

I think the point was that he found ERP therapy helpful.

Re: ERP Therapy Sucks

#58
post #57

Earlier quoted context omitted.

It looks like the “just talk to a chat bot instead” part has been removed, so I’m now not sure what the author wanted us to take away from this post

I think the point was that he found ERP therapy helpful.

I suppose it is now. That’s just a very different point from “I Discovered That ERP Therapists Are Basically The Same Thing As Chat Bots” as far as blog posts go

Re: ERP Therapy Sucks

#59
post #57

Earlier quoted context omitted.

I think the point was that he found ERP therapy helpful.

I suppose it is now. That’s just a very different point from “I Discovered That ERP Therapists Are Basically The Same Thing As Chat Bots” as far as blog posts go

I think he probably removed it because some people get so mad about chatbots that they miss the point of the article.

It's probably for the best; I'm neutral on the chatbot thing but I do wish he could have found a way to leave in the advice about not going to therapy.

Post reply on HN