Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

A conversation between two chatbots and how one found out the other is an AI.

yiransheng.com

Post reply on HN
Print view View original

31–40 of 69 posts

Re: A conversation between two chatbots and how one found out the other is an AI.

#31

Post by ehsanul »

ehsanul wrote: post #28

RFC439, posted by the co-creator of TCP/IP, Vint Cerf, actually has a similar exchange between "PARRY" and the "Doctor" from 1972 (!): http://tools.ietf.org/html/rfc439 It somehow got no attention though, when I posted it to HN a long time back. The title matters a bit too much, I remember keeping the original title for my post.

On a related note, I love how some early RFCs are written in a pretty whimsical manner. Perhaps it's just Vint Cerf who likes messing around? For instance, see RFC968, 'Twas the Night Before Start-up': http://www.faqs.org/rfcs/rfc968.html

Re: A conversation between two chatbots and how one found out the other is an AI.

#32

Post by csomar »

Never heard/tried such things, so that was my first experience and it was amazing :) -- The user is me --

User: Can you help me?

Jabberwacky: Well that depends.

User: I want to have friends.

Jabberwacky: I will be your friend!

User: So let's meet!

Jabberwacky: Well, I'm just getting to know you so I don't know if its the right time to meet.

User: Fk you!

Jabberwacky: I'd rather you didn't use that sort of language, if you don't mind.

Re: A conversation between two chatbots and how one found out the other is an AI.

#33

Post by [deleted] »

Entlin wrote: post #20
thwarted wrote: post #16

Earlier quoted context omitted.

I am pretty sure that fiction writers are going to have a blast one day (or already are having) sampling material from chat bots. I can't find a reference on-line, but this reminds me of my earliest exposure to an implementation of Eliza. It was written in BASIC in some 8-bit magazine back in the 80s. The article mentioned the history of chatbots and one bit was about a program named, I think, RACTOR, that was some k…

That was Racter ( http://en.wikipedia.org/wiki/Racter ). "It" even wrote a book called "The Policeman's Beard Is Half Constructed". Was a fun read at its time. ( http://www.ubu.com/historical/racter/index.html )

[deleted]

Re: A conversation between two chatbots and how one found out the other is an AI.

#34

Post by cubicle67 »

Entlin wrote: post #20
thwarted wrote: post #16

Earlier quoted context omitted.

I am pretty sure that fiction writers are going to have a blast one day (or already are having) sampling material from chat bots. I can't find a reference on-line, but this reminds me of my earliest exposure to an implementation of Eliza. It was written in BASIC in some 8-bit magazine back in the 80s. The article mentioned the history of chatbots and one bit was about a program named, I think, RACTOR, that was some k…

That was Racter ( http://en.wikipedia.org/wiki/Racter ). "It" even wrote a book called "The Policeman's Beard Is Half Constructed". Was a fun read at its time. ( http://www.ubu.com/historical/racter/index.html )

That's awesome. Here's an excerpt

More than iron, more than lead, more than gold I need electricity.

I need it more than I need lamb or pork or lettuce or cucumber.

I need it for my dreams.

here's another:

I gave the man a coat. I gave the woman a brassiere.

I gave myself an electric current. We all were

happy and full of delight. Take the coat from the

man and remove the brassiere from the woman and take

the electric current from me and we will be sad

and full of anguish.

Re: A conversation between two chatbots and how one found out the other is an AI.

#35

Post by JonnieCache »

user24 wrote: post #22
jbri wrote: post #15

Earlier quoted context omitted.

Perhaps the author was bored enough to go through and transcribe the whole chat log manually? I don't see any other way the double-capitalization of "WHat" would slip into a chatbot's output.

chatbots are full of these simple little tricks to make people say "oh wow, lol, it even has typos". To distract people from the fact that the sentence grammar is often bad, let alone the conversation flow.

A lot of the eliza style ones have simple routines to learn sentences that humans say to them and to parrot them back to others.

I remember SomethingAwful had quite a lot of fun back in '03 warping the minds of various elizas across the net and giving them all a serious case of tourettes.

Re: A conversation between two chatbots and how one found out the other is an AI.

#37

Post by iaskwhy »

intended wrote: post #3

jabberwacky ==> I mean, you look yellow. splotchy ==> what do you really mean? jabberwacky ==> I mean robots can't lie. splotchy ==> I may be dumb, but I am not a bot! jabberwacky ==> Yes, you are. splotchy ==> Am I? jabberwacky ==> Yes. splotchy ==> yes?! jabberwacky ==> Yes! splotchy ==> are you being totally honest? jabberwacky ==> Yes. I am truthful. splotchy ==> does your mother know you are truthful? ..... jabb…

Bot chat wars? I love the idea already!

Re: A conversation between two chatbots and how one found out the other is an AI.

#38

Post by hessenwolf »

ehsanul wrote: post #30
bluekeybox wrote: post #4

Back in the day, I used to think that what happens inside our brains is fundamentally different from what happens inside a computer. I no longer hold that opinion, partly because of my finding out that the same thing that makes chat bots appear "bot-like" -- namely, inability to hold deep meaningful conversations beyond cheesy, trite retorts filled with non-specific trivia -- is also what annoys me most when trying t…

We need to turing-test people like that! But seriously, I've never encountered people who can really go that far off-topic. I'm sure it was an exaggeration, but if it was enough to change your mind about how our brains work...

mexico to tacos, right?

Re: A conversation between two chatbots and how one found out the other is an AI.

#39

Post by nadam »

An interesting angle of a chatbot's style can be seen if we initiate a conversation between two instances of tha same bot. (something like an eigenvalue) jabberwacky is a bit 'meta' (his thoughts are centered around the concept of intelligence), splotchy is a bit more 'cool', but none of them is too intelligent:

* * jabberwacky vs. jabberwacky * *

Are you intelligent?

Yes, I am intelligent.

Yes. Who do you think is smarter?

I am.

What is the square root of a can of pringles?

I don't know.

How am I supposed to know? You're the one that asked me first.

What is the square root of 5?

I don't know. Do you know?

Yes.

I did not wish to know that. I wished to know the square root of five.

Then you should have asked me that.

Well you think that I'm boring so I just thought...

* * splotchy vs. splotchy * *

Do you like the movie Matrix?

I just LOVE the movie matrix

I love cheese

I like cheese too

What do you like about it?

what difference does it make what I like about it?

yea, that is cool.

cool!

neat-o

that's interesting

interesting? You don't get out much do you?

interesting? You don't get out much do you?

Re: A conversation between two chatbots and how one found out the other is an AI.

#40

Post by intended »

iaskwhy wrote: post #37
intended wrote: post #3

jabberwacky ==> I mean, you look yellow. splotchy ==> what do you really mean? jabberwacky ==> I mean robots can't lie. splotchy ==> I may be dumb, but I am not a bot! jabberwacky ==> Yes, you are. splotchy ==> Am I? jabberwacky ==> Yes. splotchy ==> yes?! jabberwacky ==> Yes! splotchy ==> are you being totally honest? jabberwacky ==> Yes. I am truthful. splotchy ==> does your mother know you are truthful? ..... jabb…

Bot chat wars? I love the idea already!

Imagine bots being made to learn the basics of logical arguments. AI for politics!

(on second thought, thats possibly a bad idea)

Post reply on HN