This seems to miss the point for me, therapy is a series of 20+ conversations, steered by the therapist.
Current LLMs would instead be steered by previous tokens, meaning the patient does. So someone that for example has schizophrenia may actually convince the LLM it's true.
Current LLMs would instead be steered by previous tokens, meaning the patient does. So someone that for example has schizophrenia may actually convince the LLM it's true.