Chatterbots are often integrated into the dialog systems of, for example, automated online assistants, giving them the ability of, for example, small talking or engaging in casual conversations unrelated to the scopes of their primary expert systems.


Today I signed into AIM express and was immediately messaged by a chatterbot named Kelx3duh:


Turing test assesment: failed to be believably sexxy.  Who programs these things?  Well, this guy, for one:



By the way those who have nothing to do during the day, you can chat with virtual sweetheart here. Her name is Keira and ofcourse she is very damn stupid right now with only the standard AI files. I will use people reply to her to train her when am free lol. By the way I wrote this post quite quickly without checking for errors. Sorry for the bad grammar today wlol. Am too hungry… leave your comments.

Lol, absolutely.

Not all chatterbots and their programmers are interested in getting your credit card number in exchange for something that ends with the saddest come clean-up ritual ever.  The earliest example seemed to be a lot more pleasant in fact:

ELIZA’s key method of operation (copied by chatbot designers ever since) involves the recognition of cue words or phrases in the input, and the output of corresponding pre-prepared or pre-programmed responses which can move the conversation forward in an apparently meaningful way (e.g. by responding to any input that contains the word ‘MOTHER’ with ‘TELL ME MORE ABOUT YOUR FAMILY’).  Thus an illusion of understanding is generated, even though the processing involved has been merely superficial. ELIZA showed that such an illusion is surprisingly easy to generate, because human judges are so ready to give the benefit of the doubt when conversational responses are capable of being interpreted as “intelligent”. Thus the key technique here – which characterises a program as a chatbot rather than as a serious natural language processing system – is the production of responses which are sufficiently vague and non-specific that they can be understood as “intelligent” in a wide range of conversational contexts. The emphasis is typically on vagueness and unclarity, rather than any conveying of genuine information.


I was never very good with interacting with large groups at parties so it’s some comfort to find out that the machines will conquer us via our predilection for banal chit-chat.