Machine Learning

1 readers

1 users here now

Community Rules:

Be nice. No offensive behavior, insults or attacks: we encourage a diverse community in which members feel safe and have a voice.
Make your post clear and comprehensive: posts that lack insight or effort will be removed. (ex: questions which are easily googled)
Beginner or career related questions go elsewhere. This community is focused in discussion of research and new projects that advance the state-of-the-art.
Limit self-promotion. Comments and posts should be first and foremost about topics of interest to ML observers and practitioners. Limited self-promotion is tolerated, but the sub is not here as merely a source for free advertisement. Such posts will be removed at the discretion of the mods.

founded 1 year ago

MODERATORS

communick@academy.garden

[P] I build a therapy chatbot (not another wrapper around openai API) (alien.top)

submitted 1 year ago by tsundoku-16@alien.top to c/machinelearning@academy.garden

23 comments fedilink hide all child comments

I made LLM therapist by fine-tuning an open source model using custom written and collected sessions in Cognitive Behavioral Therapy (CBT). Data contains conversations that illustrate how to employ CBT techniques, including cognitive restructuring and mindfulness.

It is mostly focused on asking insightful questions. Note: It is not production ready product. I am testing it and gathering feedback.

You can access it here: https://poe.com/PsychologistLuna

Sorry that it is on Poe but this way it was much faster than making my own mobile friendly website.

Since it's LLM, it is prone to hallucinate or give responses that might be perceived as rude. Please use it with caution.

you are viewing a single comment's thread
view the rest of the comments

[–] BigBayesian@alien.top 1 points 1 year ago (2 children)

Feedback: as others have noted, unless you live in a country where therapy isn't regulated, this is a ticking legal time bomb. If you think no one at a company like Better Help has thought about building this, you're wrong. The issues are:

Where's legal liability when someone self-harms?
Where does your training set come from? Existing therapy log datasets that don't mention the training of LLMs as a possible use case in the legal agreement that clients signed may not be usable in the way you've used them.
What's your core hypothesis? That generating therapist-language has therapeutic value? Remember that the whole profession is about indirectly developing a model of what's going on in someone else's head, and then leading them to a conclusion based on that the therapist thinks may help them (this is reductionist and overly simplistic, but I think the point holds). This level of modeling and indirection seems poorly suited to a language-generator.

[–] synthphreak@alien.top 1 points 1 year ago

print("I understand. And how did that make you feel?")

[–] Appropriate_Ant_4629@alien.top 1 points 1 year ago

But think of the upside.

With a lack of well enforced privacy policies, the data such systems can mine for

selling to real insurance companies to choose who's coverage to deny based on facebook
selling to TSA watch list vendors
extortion
etc

This project could be the next FTX + Theranos.