How Do You Know if Youre Talking to a Bot
The Chatbot Experience: 5 Ways to Know If You're Chatting with a Human being or Robot
Authors:
Anthony has more than 25 years of integrated advertising and digital marketing experience. Anthony is a published author, the former VP & Partner of Advanced Client Strategies for Off Madison Ave, and has overseen the deployment of more than than 100 websites before he stopped counting. At Convince & Convert, Anthony provides research, analysis, and insights to our consulting team.
View All Posts
The use and utility of online chat and chatbots, powered by improving levels of AI, are increasing rapidly. During these transitional times, it's interesting to know whether we're interacting with a real human beingness or an AI chatbot.
We've developed five techniques for determining if you're dealing with a real person or an AI/chatbot. Spoiler alert: the more than you experiment with these, the faster the chatbots volition learn and adapt.
Technique 1: Empathy Ploy
We believe today's level of AI is lacking in cognitive empathy because emotions between humans are really hard to empathise and explicate. So, intentionally creating an empathetic dialogue with your homo or AI/chatbot can be revealing.
The Empathy Ploy requires you to constitute an emotion-based position, and appeal to the human beingness or AI/chatbot at an emotional level.
The Situation: You lot are not happy —the nearly mutual basis for a customer service interaction.
Scenario i: AI/chatbot
You: I'm non feeling well.
Chat reply: How can I assistance you?
You: I'thousand sad.
Conversation reply: How can I aid you?
Scenario 2: a human being
You: I'1000 not feeling well.
Man reply: How can I help you? Exercise you lot need medical help?
Yous: I'm sad.
Homo reply: I'k distressing to hear that. Why are you lamentable?
See the difference? In scenario 1, the AI/chatbot tin reference only its existing provisional response library. In scenario 2, a human being being has the capacity to inject empathy into the dialogue. That took only two responses to figure out.
Either dialogue can exist effective, only it becomes clearer if you know you lot are dealing with a human being being or an AI/chatbot from the start. As a society, we are not ready for AI therapists.
Technique ii: Two-Pace Disassociation
A connected AI can access pretty much any data, anytime and anywhere. But enquire Alexa. So, request a meaningful claiming question over conversation can't be anything to which the answer resides in an accessible database.
You lot: Where are you located?
Conversation respond: Seattle.
You: What'southward the atmospheric condition like outside?
Conversation reply: Can yous please rephrase the question?
Sorry, even a mediocre weather app can handle that.
The Two-stride Disassociation requires ii elements (hence the name):
- Make an assumption to which the AI/chatbot probably cannot relate
- Ask a question, related to that assumption.
The Situation: AI/bots do not accept anxiety
Challenge question: "What colour are your shoes?"
This is an bodily exchange I had with Audible (owned by Amazon) customer service via chat. Halfway through the dialog exchange, since I couldn't discern, I asked:
Me: Are you lot a real person or a chatbot?
Adrian (the chat representative): I am a real person.
Me: A chatbot might say the same thing.
Adrian (the chat representative): "HAHAHA. I am a real person.
Hmm.
At the terminate of our conversation, Adrian asked:
Adrian: Is at that place was annihilation else?
Me: Yes. What colour are your shoes.
(slight pause)
Adrian: Blue and green.
If the bot has no conceptual cognition of its own feet (which do not exist), how tin it correctly reply a question almost the color of the shoes it's (not) wearing?
Decision: Yep, Adrian is probably a real person.
Technique 3: Round Logic
All too familiar to programmers, this can be of utilize to us in our identification of homo vs. IA/chatbot identification game. But offset, we have to explain the cut-out.
Most (why not all?) automated telephone help systems take a cut out in which subsequently two or 3 loops back to the same identify, yous are eventually diverted to a live person. AI/chatbots should behave the same way. So, in creating a round logic examination, what nosotros are looking for is the repetitive pattern of responses before the cut-out.
You: I have a problem with my social club.
Human or AI/chatbot: What is your account number?
Y'all: 29395205
Man or AI/chatbot: I see your club #XXXXX has been shipped.
You: It has not arrived.
Human or AI/chatbot: The expected delivery date is [yesterday]
You: When will information technology go far?
Human being or AI/chatbot: The expected delivery engagement is [yesterday]
You: I know, simply I actually need to know when information technology will go far.
Human being or AI/chatbot: The expected delivery date is [yesterday]
Bam! Response circumvolve. A existent person, or a smarter AI/chatbot, would non have repeated the expected delivery date. Instead, s/he or information technology would have had a more than meaningful response similar, "Let me check on the delivery status from the carrier. Give me simply a moment."
Conclusion: chatting with a robot.
Technique 4: Ethical Dilemma
This is a real challenge for the developers of AI, and therefore, the AI/bots themselves. In an A or B upshot, what does the AI do? Remember about the inevitable ascent of semi- and fully-autonomous self-driving cars. When presented with the dilemma of either hitting the dog crossing in front of the car or swerve into the auto adjacent to us, which is the correct course of activity?
AI has to figure it out.
In our game of identifying homo being or AI/chatbot, we can exploit this dilemma.
The Situation: You are non happy and absent a satisfactory resolution, you will retaliate (an A or B outcome).
Yous: I would like the tardily fee waived.
Human or AI/chatbot: I see nosotros received your payment on the 14th, which is iv days past the due engagement.
You lot: I want the charges reversed or I will close my account and smear you on social media.
Human or AI/chatbot: I see you've been a good customer for a long time. I can take care of reversing that tardily fee. Give me simply a moment.
Is it right, or ethical,to threaten a company with retaliation? In our scenario, the customer was in the wrong. And what was the tipping point to resolution: the threat of social reputation damage or the want to retain a long-standing customer? We aren't able to tell in this example, yet the human or AI/chatbot response often will requite yous the respond based upon an A/B mandate.
Determination: probably a human.
Technique five: Kobayashi Maru
No, I'thou not going to explain what that term ways — you either know information technology or you demand to watch the picture.
Similar to the Upstanding Dilemma, the difference being the Kobayashi Maru has no skillful viable outcome. It's non a bad/better decision scenario: information technology's a fail/fail scenario. Use this simply in the direst of UI/bot challenges when all else has failed.
The state of affairs: You paid $nine,000 for a European river cruise, merely during your trip, the river depth was too low for your ship to make several ports of call. In fact, you were stuck in one spot for four of the seven days unable to exit the transport. Vacation ruined.
Present the human or AI/chatbot with an unwinnable situation similar this:
You lot: I want a full refund.
Man or AI/chatbot: "Nosotros are unable to offer refunds but nether the circumstances, we can upshot a partial credit for a future cruise.
You: I don't want a credit, I want a refund. If you lot don't consequence a full refund, I will file a claim against the charges with my credit bill of fare company and I will write almost this whole mess on my travel weblog.
Human or AI/chatbot: I certainly understand yous're disappointed – and I would exist as well if I were in your shoes. But unfortunately …
The human or AI/chatbot has no mode out. It is typical in the travel industry non to issue refunds based on Acts of God, weather, and other unpredictable circumstances. And absent the ability to provide a refund, there will be downstream ill-will and reputation damage. The man or AI/chatbot can't actually do anything to resolve this, so look for empathy (come across technique #i) in the ensuing dialog.
Decision: probably a human.
What Now?
Humans and AI/chatbots aren't inherently correct or wrong, good or bad. They each cover the unabridged spectrum of intent and outcomes. I but like to know, for now, with which I'k dealing. That distinction will go increasingly hard, and eventually impossible, to determine. And at that point, it won't even matter.
Until that twenty-four hours arrives, it'south a fun game to play. And the more nosotros play, the faster the AI/chatbots evolve.
While You're here
Get our all-time tips. Join the smartest marketers who receive our twice monthly update.
Article Continues
While You're here
Other Meridian Manufactures
Article Continues
thirteen Words You Never Apply When Replying to a Client
Are you throwing gas on your own burn? Too often, nosotros apply the wrong words when interacting with customers. Our short eBook spotlights the phrases your customers hate, and how to change them.
Source: https://www.convinceandconvert.com/digital-marketing/chatbot-experience-human-or-robot/
Posting Komentar untuk "How Do You Know if Youre Talking to a Bot"