The mysterious nature of bots
A couple of years ago made a joke of some kind, as he often does. The subject of the joke was , a uniquely Twitter oddity and likely the to have ever lived. This seemed like a prime opportunity for silliness, so after a bit of coding was born. Little did I know this would be but the first of .
Dear god, just realised that I care about conceptual understanding.
— Jack Scanlan ebooks (@scanlan_ebooks)
chatbots have a long history in programming, being very easy toy examples of a simple but powerful mathematical model which is used for a whole lot of . The classic Markov text generator maintains a probability map of which words are more or less likely to come after some number of preceding words, and builds a sentence by following it from a given start point.
The is a variation on this. Instead of linearly chaining words, it starts with an intact sentence from the corpus and mixes it with one or more other sentences in a manner similar to . The Markov model is used to select the junction sites where this recombination occurs. This seems to strike a nice balance between diversifying the output and avoiding complete gibberish; the sentences it produces are grammatically correct more often than not. (well, assuming the source is!)
This has proliferated somewhat, and I have no idea how many of the various _ebooks accounts are using my Ruby gem or how modified they are. There have been bots based on , , and all manner of strange text corpora. Kevin Nguyen wrote a very about , deployed by .
What I find much more interesting than the bots themselves though is the way people interact with them. These generally fall into three groups:
- Those familiar with Markov chains who are being tongue-in-cheek about it
- Non-programmers experiencing to various degrees
- People who should probably never be relied upon to judge a
The third group is more populous than you might expect, especially if you include ESL speakers. My bots will try to imitate human interaction patterns, responding to mentions to come up with something vaguely related to the input, and a slight random delay to avoid appearing superhuman. They will also follow back and occasionally favorite or RT tweets they find sufficiently interesting.
Some examples of amusing events in recent history:
mcc_ebooks and the robot uprising
I think is my favorite overall, just because and her friends are already so suffused with baffling surreal humor that it just sort of amplifies it.
We could just stay like this forever while flashing bands of color horizontally across the screen
— mcc ebooks (@mcc_ebooks)
People tend to give it the benefit of the doubt, which is often very sweet and heart-warming.
Aww, you have a girlfriend? Bots in love, so adorable!
— Erika Sorensen (@eiridescent)
As the original human tweets at and about the bot, more bot-related statements enter the corpus, so it becomes "self-aware".
I feel like we just had a moment.
— Kevin Snow (@starguarded)
Which of course, has only one logical endpoint.
I stand up (gain the ability to walk), to become naked
— mcc ebooks (@mcc_ebooks)
m1sp1dea_ebooks spooks Rackspace security
uses a combined corpus consisting of myself and 's tweets. It's kind of a freakish hybrid. (people keep anyway, somehow)
Anxiety is not a big truck.
— Melissa × Mispy (@m1sp1dea_ebooks)
Of course since spends a lot of time talking about infosec, it was inevitable that the bot would one day announce it had found a vulnerability.
Hi! Please let us know if you find anything should be aware of
— Elizabeth Jurewicz (@RackerLiz)
And not do very much to discourage the idea.
Please send details to [email protected] , we'll see how we can help. ( cc )
— Elizabeth Jurewicz (@RackerLiz)
Fortunately, a human quickly intervened.
oh I’m sorry, this is a bot who mashes up tweets :(
— Melissa (@0xabad1dea)
The political intrigues of TonyAbotMHR
During the last Australian federal election season, someone made a joke about and his propensity for Markov-like meaningless rambling. Thus, was born, using a slightly different algorithm that replaces nouns with random other nouns.
But ladies and gentlemen, it's just got worse since Julia Gillard has become the Prime Minister of this napkin.
— Tony A Bot (@TonyAbotMHR)
Occasionally, he is mistaken for the real thing, by endearingly optimistic citizens who seemingly believe the denizens of high politics are likely to engage in individual discourse with them.
I voted green it would appreciated if you did take sometime to see what they offered. Especially Mining Co. should pay HTax
— Mimi Savy deChermont (@ameliatdales)
There's been at least one truly epic debate, covering everything from genetically modified giraffes to the local entertainment industry.
This is getting a bit cryptic but yep, i need to have no reservations about putting my name to any actions hypothetical or not
— Sir Tennly Loverock (@EdHightackle)
This man has since been elected Prime Minister, to our great dismay.
winocm_ebooks and the jailbreak swarm
has the highest follower count of my Twitter friends by a large margin, largely on account of her role in the . Sadly this means she is constantly pestered by people demanding the release of various things.
plz don't ignore me
I want to ask about 7.1 JB
Plz answer 😣😣
— عبدالله النصر (@abdullahnssr)
Maybe I should make a Markov chain bot respond to all requests for a 7.1 jailbreak on this account… calling !
— winocm (@winocm)
Fortunately, this was a trivial extension to make to .
make_bot(bot, "winocm") do |gen|
EM.next_tick do
bot.stream.track("@winocm") do |tweet|
text = tweet[:text].downcase
if !tweet[:user][:screen_name].include?("_ebooks") && (text.include?("7.1") || text.include?("jailbreak") || text.split.include?("jb"))
bot.reply(tweet, "@#{tweet[:user][:screen_name]} " + gen.model.make_response(tweet[:text]))
end
end
end
end
It works really quite surprisingly well. People mention , receive a reply from , and proceed to engage with it, seemingly unaware that their jailbreaking deity has been replaced with a robot.
oh wait, I broke 7.x by installing 7.1 improperly I think, I should fix that...
— winocm_ebooks (@winocm_ebooks)
These conversations go on for many, many pages. A few bold individuals even requested the bot's hand in marriage:
Please will you marry me?
— Drake Kanjuani (@SecretAgentZ3R0)
if I love you will you marry me and find me exploits
— Ninty Apple (@nintendoapple_)
I'm fairly sure this isn't legal anywhere yet. Maybe Japan.
Can we draw any interesting conclusions from all of this? Probably not. I do like to think, though, that the readiness with which people engage with the bots speaks well of our capacity to accept that which is fundamentally different from us. Should true non-human intelligence appear, I hope we will be similarly ready to adapt our culture around it.