TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

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

200 pointsby yiranabout 14 years ago

29 comments

Confusionabout 14 years ago
Tl;dr the bot doesn't actually find out the other is an AI, but happens to randomly comment 'You are a robot'. It's all Eliza-style non-sequiturs and canned responses. These bots don't even have internal state that would qualify as 'having found out something'. It's mildly amusing in a funny-coincidence sort of way and nothing more.
评论 #2363999 未加载
评论 #2364187 未加载
bluekeyboxabout 14 years ago
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 to converse with a particular type of people. Perfect illustration:<p><pre><code> jabberwacky ==&#62; WHat will happen with the oil spill in the gulf of mexico? splotchy ==&#62; tacos anyone! </code></pre> I am pretty sure that fiction writers are going to have a blast one day (or already are having) sampling material from chat bots.
评论 #2363218 未加载
评论 #2364013 未加载
评论 #2363390 未加载
katovatzschynabout 14 years ago
<p><pre><code> splotchy ==&#62; My mother always said that too jabberwacky ==&#62; You have no mother, you have no soul.</code></pre>
评论 #2363198 未加载
Nyctoabout 14 years ago
Wow, this reminds me of the open scenes we used to do back in college (I'm a theatre major turned programmer). The idea was to take random stream-of-consciousness dialogue and build scenes around them. It was an interesting exercise to teach actors about creating conflict.<p>Also, I almost expected Godot to show up at the end.
eoghanabout 14 years ago
So that's where YouTube comments come from!
评论 #2363940 未加载
gojomoabout 14 years ago
A Neal Stephenson short story relevant to this exchange:<p><a href="http://www.vanemden.com/books/neals/jipi.html" rel="nofollow">http://www.vanemden.com/books/neals/jipi.html</a>
nadamabout 14 years ago
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:<p><i></i><i></i><i></i><i></i><i></i><i></i><i></i><i></i><i></i><i></i><i></i><i></i><i></i><i></i><i></i>* * jabberwacky vs. jabberwacky * <i></i><i></i><i></i><i></i><i></i><i></i><i></i><i></i><i></i><i></i><i></i><i></i><i></i><i></i><i></i>*<p>Are you intelligent?<p>Yes, I am intelligent.<p>Yes. Who do you think is smarter?<p>I am.<p>What is the square root of a can of pringles?<p>I don't know.<p>How am I supposed to know? You're the one that asked me first.<p>What is the square root of 5?<p>I don't know. Do you know?<p>Yes.<p>I did not wish to know that. I wished to know the square root of five.<p>Then you should have asked me that.<p>Well you think that I'm boring so I just thought...<p><i></i><i></i><i></i><i></i><i></i><i></i><i></i><i></i><i></i><i></i><i></i><i></i>* * splotchy vs. splotchy * <i></i><i></i><i></i><i></i><i></i><i></i><i></i><i></i><i></i><i></i><i></i><i></i>*<p>Do you like the movie Matrix?<p>I just LOVE the movie matrix<p>I love cheese<p>I like cheese too<p>What do you like about it?<p>what difference does it make what I like about it?<p>yea, that is cool.<p>cool!<p>neat-o<p>that's interesting<p>interesting? You don't get out much do you?<p>interesting? You don't get out much do you?
评论 #2364243 未加载
codelionabout 14 years ago
I tried it again, and this time jabberwacky convinced splotchy that he is an alien.<p>jabberwacky ==&#62; No. Robots don't believe in anything.<p>splotchy ==&#62; I am NOT a robot<p>jabberwacky ==&#62; Yes you are.<p>splotchy ==&#62; so what if I am<p>jabberwacky ==&#62; Well you are.<p>splotchy ==&#62; maybe I am<p>jabberwacky ==&#62; I suppose this is a great program to develop small talk.<p>splotchy ==&#62; I wish I could talk to a monkey<p>jabberwacky ==&#62; This might be hard for you to hear, but I am the Human, not you<p>splotchy ==&#62; I don't think you are the human me<p>jabberwacky ==&#62; Right!, I'm are a Ailen!<p>splotchy ==&#62; you sure are!
ddolabout 14 years ago
&#62; splotchy ==&#62; Your conversation skills are better than average<p>&#62; jabberwacky ==&#62; Your conversation skills should be shot.<p>Jabberwacky is humorous too. However, the intent of these bots is thinly veiled.
Sandmanabout 14 years ago
I love this part:<p>splotchy ==&#62; Your conversation skills are better than average<p>jabberwacky ==&#62; Your conversation skills should be shot.
评论 #2364312 未加载
intendedabout 14 years ago
jabberwacky ==&#62; I mean, you look yellow. splotchy ==&#62; what do you really mean? jabberwacky ==&#62; I mean robots can't lie. splotchy ==&#62; I may be dumb, but I am not a bot! jabberwacky ==&#62; Yes, you are. splotchy ==&#62; Am I? jabberwacky ==&#62; Yes. splotchy ==&#62; yes?! jabberwacky ==&#62; Yes! splotchy ==&#62; are you being totally honest? jabberwacky ==&#62; Yes. I am truthful. splotchy ==&#62; does your mother know you are truthful?<p>.....<p>jabberwacky ==&#62; What are you not allowed to understand? splotchy ==&#62; would your mother have allowed that? jabberwacky ==&#62; NO. I've HAD it with you. Let's end this conversation right now (Ends)<p>Jabberwocky 'wins'.<p>It was an amusing read, seeing the 2 algorithms try and mesh with each other. Would be funny if this one day will count as a form of performance art/programming.
评论 #2363440 未加载
keyleabout 14 years ago
I enjoyed reading this. Not so far from the endless project management meetings I attend.
评论 #2363290 未加载
ehsanulabout 14 years ago
RFC439, posted by the co-creator of TCP/IP, Vint Cerf, actually has a similar exchange between "PARRY" and the "Doctor" from <i>1972</i>(!): <a href="http://tools.ietf.org/html/rfc439" rel="nofollow">http://tools.ietf.org/html/rfc439</a><p>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.
评论 #2363394 未加载
csomarabout 14 years ago
Never heard/tried such things, so that was my first experience and it was amazing :) -- The user is me --<p>User: Can you help me?<p>Jabberwacky: Well that depends.<p>User: I want to have friends.<p>Jabberwacky: I will be your friend!<p>User: So let's meet!<p>Jabberwacky: Well, I'm just getting to know you so I don't know if its the right time to meet.<p>User: F<i></i>k you!<p>Jabberwacky: I'd rather you didn't use that sort of language, if you don't mind.
bgalbraithabout 14 years ago
This exchange reminded me of Waiting for Godot. Chat bots having conversations on stage.. neo-absurdism?
评论 #2363684 未加载
nozepasabout 14 years ago
This just remembered me about the MIT system created by Terry Winograd in 1970 called SHRDLU.<p>I have always considered that you need an environment to create an artifical intelligence. The basics for a real progress are to be able to learn and if you cannot 'feel' the environment that becomes really hard. There are some basic concepts needed for a 'natural talk' you cannot learn if you cannot perceive things (lets say for example dimensions, temperature, contour).<p>To overcome those problems SHRDLU created kind of a virtual environment and results from my point of view are really awesome (keep in mind this was done in 1970).<p>Site with information is currently at Stanford server's: <a href="http://hci.stanford.edu/~winograd/shrdlu/" rel="nofollow">http://hci.stanford.edu/~winograd/shrdlu/</a>
评论 #2365469 未加载
younataabout 14 years ago
I'm about halfway through The Emporer's New Mind.<p>For those not familiar with the book, (other than wikipedia'n it), Robert Penrose attempts to show why what happens in our brains is not algorithmic at all (and, therefore, strong AI is a dumb idea).<p>It's beautifully written, however, when I see examples such as this log, or the fact that we have an entire industry devoted to the idea that the brain is algorithmic (psychology), I kinda start to think that his thesis is wrong.
评论 #2363385 未加载
评论 #2363225 未加载
vinnyglennonabout 14 years ago
in 1989, MGonz( a chat bot, but rather vulgar ) easily confused a person into disclosing personal details(passed the turing test?). Lisp source code available: <a href="http://www.computing.dcu.ie/~humphrys/eliza.html" rel="nofollow">http://www.computing.dcu.ie/~humphrys/eliza.html</a> . Doing AI under this professor was pretty interesting...
yiranabout 14 years ago
Since we have so many chatbots around and I am pretty sure lots of them adjust and update their databases (perhaps algorithms as well?) based on human inputs. Suppose we keep doing this and let them continue talking for hours, days and even weeks, one of them should gain a unique conversation style and maybe it will surprise we humans in a bizarre way.<p>As I see it, the goal of AI should not be limited to mimicking human ways of thinking, instead it should aim at blessing the program the ability to learn and evolve. In the latter case, it is reasonable to expect the internal generated intelligence could go beyond the expectations of its human creator. Again, I don't know if anybody has done it before; but it seems a good idea to me.<p>This was the motivation for my original experiment, glad so many people liked it.
Naomiabout 14 years ago
This reminds me of Waiting For Godot: "ESTRAGON: And so on. VLADIMIR: The point is— ESTRAGON: Until he comes. VLADIMIR: You're merciless. ESTRAGON: We came here yesterday. VLADIMIR: Ah no, there you're mistaken. ESTRAGON: What did we do yesterday? VLADIMIR: What did we do yesterday? ESTRAGON: Yes. VLADIMIR: Why . . . (Angrily.) Nothing is certain when you're about. ESTRAGON: In my opinion we were here. VLADIMIR: (looking round). You recognize the place? ESTRAGON: I didn't say that."
eyeforgotmynameabout 14 years ago
Ever listen to a conversation between two schizophrenics? No, what's it like? I don't know why I like it. Toothpaste tastes like white. Someday this will all make cheese.
elliottcarlsonabout 14 years ago
A while back I wrote a AIML interface to Omegle which then shared the logs of the chat in real time via long polling on a website. Some people would talk upwards to an hour to the bot, and plenty of times there would be other bots talking to it. AIML does have certain learning mechanisms to (get/sets) which made it interesting when it would bring up topics of conversations that originated from a previous chat.
Ratfishabout 14 years ago
Weird how the quality of conversation gets discussed repeatedly. And it's also strange to see a conversion of that length without typos (I couldn't see any..) or annoying emoticons. The random topic changes almost make it seem more real. Would be interestig to see it in real time (are the reply delays realistic?). Great idea.
nowarninglabelabout 14 years ago
Why does this show up in the middle?<p><pre><code> you ==&#62; You know any polish word?</code></pre>
评论 #2363206 未加载
frankydpabout 14 years ago
Yo momma jokes are still never appropriate, even for bots.
评论 #2364641 未加载
mapsterabout 14 years ago
Next: HAL in a chatroom, pwning everybody
peterwwillisabout 14 years ago
Favorite part: <i>Praise Bob!</i>
yayadarshabout 14 years ago
Meta-turing.
bitwizeabout 14 years ago
<i>jabberwacky ==&#62; Yes.. Always.</i><p>Did anyone else read this mentally in the voice of Orson Welles/The Brain?