I tried it a fair bit and it seemed to just give vague questions as answers. I wondered why but it was essentially modeled to play a psychiatrist in terms of the sort of language one might use,

So if you write “unhappy” or smth it’ll goe “why are you unhappy” /“did you come to me because you’re unhappy” etc.

Very simple ofc but would’ve been impressive 60y ago.

If you input *help you’ll see commands and *cacm repeats the ELIZA / DOCTOR conversation from the original paper so you can sort of see what it’s capable of when the writer knows pretty much exactly what to prompt. (There’s still some variance in but eh…)