Scientists have just resurrected “ELIZA,” the world’s first chatbot, from long-lost computer code — and it still works extremely well.
Using dusty printouts from MIT archives, these “software archaeologists” discovered defunct code that had been lost for 60 years and brought it back to life.
Huh, I never knew that the version of Eliza many of us have tried out was based on the original author’s academic paper and not the original source code.
Write enough IF-THEN lines of code you can simulate anything. Look at Undertale and how it used thousands of conditionals. You know what’s more impressive than ELIZA’s code? Infocom’s text parser.
Eliza or its faithful clone comes with every Emacs. To conslult your doctor type M-x doctor
Stan Lee is alive and well apparently.
Elizalsior!
Jeez:
I AM NOT SURE I UNDERSTAND YOU FULLY
i’m sorry
IS IT BECAUSE YOU ARE SORRY THAT YOU CAME TO ME
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…)
Yeah it talks down to you kinda funny but limited on knowledge. Kept asking if I was sure. Then when I said yes just replied I understand.
You need to know the keywords to have an actual conversation with it if you even can.
Still pretty neat to bring back a sixy year old code.
Sounds like an old school text adventure.
Is this the program that was mentioned in Century of Self?
Link to try it out: https://sites.google.com/view/elizaarchaeology/try-eliza
Pretty sure I have an “ecceliza.exe” somewhere.