Professor Behind Two Chatbots Chatting Discusses What Happened

from the mimicing-is-how-we-learn dept

By now, I assume you’ve already seen the two chatbots talking to each other, but on the off-chance you haven’t (or in case you just want to see it again), here it is:


The video went crazy viral quickly, and the folks at The Alyona Show moved quickly and got the professor behind the project, Hod Lipson, on the show to talk about the experiment:


It’s an interesting conversation, but the one point that really caught my attention was over the question of whether or not the bots “understood” what they were saying. The obvious answer is “of course not, they’re just bots,” but Lipson made an interesting point: at times it’s not clear that actual people know what they’re saying. Many people just repeat stuff they’ve heard elsewhere — which is how Cleverbot is programmed to work. He also notes that this is effectively how children learn to speak and to think, by repeating what others say. Of course, there’s still a huge difference, and there’s nothing in Cleverbot that will ever take all these pieces and take it to the next level of conscious thought, but it’s still a neat concept.

Filed Under: , ,

Rate this comment as insightful
Rate this comment as funny
You have rated this comment as insightful
You have rated this comment as funny
Flag this comment as abusive/trolling/spam
You have flagged this comment
The first word has already been claimed
The last word has already been claimed
Insightful Lightbulb icon Funny Laughing icon Abusive/trolling/spam Flag icon Insightful badge Lightbulb icon Funny badge Laughing icon Comments icon

Comments on “Professor Behind Two Chatbots Chatting Discusses What Happened”

Subscribe: RSS Leave a comment
17 Comments
Zauber Paracelsussays:

I’m somewhat reminded of another experiment that pits two chatbots against one another. ELIZA, a bot meant for use in psychotherapy, and Racter, an “artificially insane” storyteller.

Here’s a copy of the conversation:

eliza: Hello. Please state your problem.

racter: Excellent! Excuse me a minute while I attend to some business. I will be right back.

eliza: Why do you need to tell me excuse while you attend to some business?

racter: Is it better to need or to despise? Why is it that I do need to tell you to excuse myself to attend to some business? Because electrons are brave. Braveness is nice, don’t you think? And the needers all insist upon it. Do you imagine I am a Communist?

Source: http://www.stanford.edu/group/SHR/4-2/text/dialogues.html

Chinese room

It’s an interesting conversation, but the one point that really caught my attention was over the question of whether or not the bots “understood” what they were saying. The obvious answer is “of course not, they’re just bots,” but Lipson made an interesting point: at times it’s not clear that actual people know what they’re saying.

This is basically Searle’s Chinese room, isn’t it?

That's a Reacreation of Most People in Software Form

Many people just repeat stuff they’ve heard elsewhere — which is how Cleverbot is programmed to work. He also notes that this is effectively how children learn to speak and to think, by repeating what others say. Of course, there’s still a huge difference, and there’s nothing in Cleverbot that will ever take all these pieces and take it to the next level of conscious thought, but it’s still a neat concept.

==========================

I’d say these bots are now at the same or higher level of “consciousness” than 85% of the human race…at least those I talk to for socially-mandatory reasons.

Anonymoussays:

We need to shut them down now before they become sentient and in a completely illogical manner manage to take control of all of the defense systems in the world and try killing off humanity. Then we will have to protect a really hot chick from a murderous robot that when it gets stopped instead of trying to kill her grandfather or other ancestor decides to try 3 more times.

how to talk to each other two chatbots.

the easiest way to do two chatbots speak to each other is to copy a literal phrases and write them into the other.
it is obvious that the video was mounted using individual pieces of processing.
what the video reveals is that the answers are too fast and there is no pause between them.
then this video is simply a way to better present the topic discussed.
I am the programmer of cl0ne (zero inside clone) dot com.
if you want to test my chatbot with other goto http://www.cl0ne.com
copy and past the response from my chatbot to another.

Leave a Reply to The eejit Cancel reply

Your email address will not be published. Required fields are marked *

Have a Techdirt Account? Sign in now. Want one? Register here

Comment Options:

Make this the or (get credits or sign in to see balance) what's this?

What's this?

Techdirt community members with Techdirt Credits can spotlight a comment as either the "First Word" or "Last Word" on a particular comment thread. Credits can be purchased at the Techdirt Insider Shop ┬╗

Follow Techdirt

Techdirt Daily Newsletter

Techdirt Insider Discord
The latest chatter on the Techdirt Insider Discord channel...
Loading...
Older Stuff
13:40 It's Great That Winnie The Pooh Is In The Public Domain; But He Should Have Been Free In 1982 (Or Earlier) (35)
12:06 Norton 360 Now Comes With Crypto Mining Capabilities And Sketchy Removal Process (28)
10:45 Chinese Government Dragnet Now Folding In American Social Media Platforms To Silence Dissent (14)
10:40 Daily Deal: The 2022 Ultimate Cybersecurity Analyst Preparation Bundle (0)
09:29 A Fight Between Facebook And The British Medical Journal Highlights The Difficulty Of Moderating 'Medical Misinformation' (9)
06:29 Court Ruling Paves The Way For Better, More Reliable Wi-Fi (4)
20:12 Eighth Circuit (Again) Says There's Nothing Wrong With Detaining Innocent Minors At Gunpoint (15)
15:48 China's Regulatory War On Its Gaming Industry Racks Up 14k Casualties (10)
13:31 Chinese Government Fines Local Car Dealerships For Surveilling While Not Being The Government (5)
12:08 Eric Clapton Pretends To Regret The Decision To Sue Random German Woman Who Listed A Bootleg Of One Of His CDs On Ebay (29)
10:44 ICE Is So Toxic That The DHS's Investigative Wing Is Asking To Be Completely Separated From It (29)
10:39 Daily Deal: The 2022 Complete Raspberry Pi And Arduino Developer Bundle (0)
09:31 Google Blocked An Article About Police From The Intercept... Because The Title Included A Phrase That Was Also A Movie Title (24)
06:22 Wireless Carriers Balk At FAA Demand For 5G Deployment Delays Amid Shaky Safety Concerns (16)
19:53 Tenth Circuit Denies Qualified Immunity To Social Worker Who Fabricated A Mother's Confession Of Child Abuse (35)
15:39 Sci-Hub's Creator Thinks Academic Publishers, Not Her Site, Are The Real Threat To Science, And Says: 'Any Law Against Knowledge Is Fundamentally Unjust' (34)
13:32 Federal Court Tells Proud Boys Defendants That Raiding The Capitol Building Isn't Covered By The First Amendment (25)
12:14 US Courts Realizing They Have A Judge Alan Albright Sized Problem In Waco (17)
10:44 Boston Police Department Used Forfeiture Funds To Hide Purchase Of Surveillance Tech From City Reps (16)
10:39 Daily Deal: The Ultimate Microsoft Excel Training Bundle (0)
09:20 NY Senator Proposes Ridiculously Unconstitutional Social Media Law That Is The Mirror Opposite Of Equally Unconstitutional Laws In Florida & Texas (25)
06:12 Telecom Monopolies Are Exploiting Crappy U.S. Broadband Maps To Block Community Broadband Grant Requests (7)
12:00 Funniest/Most Insightful Comments Of 2021 At Techdirt (17)
10:00 Gaming Like It's 1926: Join The Fourth Annual Public Domain Game Jam (6)
09:00 New Year's Message: The Arc Of The Moral Universe Is A Twisty Path (33)
19:39 DHS, ICE Begin Body Camera Pilot Program With Surprisingly Good Policies In Place (7)
15:29 Remembering Techdirt Contributors Sherwin And Elliot (1)
13:32 DC Metro PD's Powerful Review Panel Keeps Giving Bad Cops Their Jobs Back (6)
12:11 Missouri Governor Still Expects Journalists To Be Prosecuted For Showing How His Admin Leaked Teacher Social Security Numbers (39)
10:48 Oversight Board Overturning Instagram Takedown Of Ayahuasca Post Demonstrates The Impossibility Of Content Moderation (10)
More arrow
This site, like most other sites on the web, uses cookies. For more information, see our privacy policy. Got it