“The truth isn’t the truth until people believe you, and they can’t believe you if they don’t know what you’re saying, and they can’t know what you’re saying if they don’t listen to you, and they won’t listen to you if you’re not interesting, and you won’t be interesting unless you say things imaginatively, originally, freshly.”
Provocative headline to drive clicks, but there is truth here that everyday advertising agencies just DO NOT UNDERSTAND.
Simply put, content marketing doesn’t work because it needs two attributes to be successful, a long-term commitment and high-quality content. And both of these requirements have high demands in terms of time and effort. Because of this, they are often ignored in an attempt to make content marketing more scalable and easier to deploy.
But unlike SEO and PPC, you’re not dealing with an algorithm when it comes to content marketing. You’re dealing with the reactions and emotions of your living, breathing customers. And that can’t be gamed, hacked, or exploited. Instead, you need to plan and deploy a content marketing campaign with the same care and attention that you would any other major company initiative.
Once you know who they are you want to help them. You do this by solving their problems. So, instead of producing content that’s all about you and your company, you should produce content that answers questions and helps them solve the challenges they face. As I’ve stated many times before, no one wants to download your brochure.
This means you shouldn’t be killing yourself to produce new content every single day. But rather, you should focus on producing high-quality pieces. As long as you’re doing that consistently, then arbitrary cadences don’t matter as much.
If you’re a fan of Sherry Turkle’s Alone Together, this will hit you in all the right places…
In many instances, the researchers observed children persistently obstructing the robot. Sometimes a child would step aside when asked by the robot, but then would quickly come back in front of it. Other children started ignoring the robot’s requests and just stood in front of it. In at least one situation (above), a child started to verbally express her intention to block the robot (“No-no”), when requested to move. Other children joined her in obstructing the robot and saying it couldn’t go through.
According to the study, “Escaping from Children’s Abuse of Social Robots,” obstruction like this wasn’t nearly the worst of it. The tots’ behavior often escalated, and sometimes they’d get violent, hitting and kicking Robovie (below). They also engaged in verbal abuse, calling the robot “bad words.” (The researchers did not disclose what bad words may have been used, but they mention that one kid called the robot “idiot” eight times.)
The researchers say they observed the children “acting violently” toward the robot in several occasions: Bending the neck, hitting with plastic bottle, hitting with ball, throwing a plastic bottle.
The Japanese group didn’t just document the bullying behavior, though; they wanted to find clever ways of helping the robot avoid the abusive situations. They started by developing a computer simulation and statistical model of the children’s abuse towards the robot, showing that it happens primarily when the kids are in groups and no adults are nearby.
Next, they designed an abuse-evading algorithm to help the robot avoid situations where tiny humans might gang up on it. Literally tiny humans: the robot is programmed to run away from people who are below a certain height and escape in the direction of taller people. When it encounters a human, the system calculates the probability of abuse based on interaction time, pedestrian density, and the presence of people above or below 1.4 meters (4 feet 6 inches) in height. If the robot is statistically in danger, it changes its course towards a more crowded area or a taller person. This ensures that an adult is there to intervene when one of the little brats decides to pound the robot’s head with a bottle (which only happened a couple times).
“McCulloch argues that female teenagers are actually ‘language disruptors’ — innovators who invent new words that make their way into the vernacular. ‘To use a modern metaphor, young women are the Uber of language,’ she writes.”
Our spaceLab team is having fun with Artificial Neural Networks…
Chatting with robots absolutely fascinates me. I’ve received two telemarketing calls for secondary education that was merely voice-clips served by an algorithm based on my responses. But that wasn’t evident until about the 25 second mark. Pretty good 2015 Turing test! I got one into a 3 minute loop asking it weird things, actually.
Check this out…
Conversational modeling is an important task in natural language understanding and machine intelligence. Although previous approaches exist, they are often restricted to specific domains (e.g., booking an airline ticket) and require hand-crafted rules. In this paper, we present a simple approach for this task which uses the recently proposed sequence to sequence framework. Our model converses by predicting the next sentence given the previous sentence or sentences in a conversation.
Human: who is skywalker ?
Machine: he is a hero .
Human: who is bill clinton ?
Machine: he ’s a billionaire .
Human: is sky blue or black ?
Machine: blue .
Human: does a cat have a tail ?
Machine: yes .
Human: does a cat have a wing ?
Human: can a cat fly ?
Machine: no .
Human: how many legs does a cat have ?
Machine: four , i think .
Human: how many legs does a spider have ?
Machine: three , i think .
Human: how many legs does a centipede have ?
Machine: eight .
Human: what is the color of the sky ?
Machine: blue .
Human: what is the color of water ?
Machine: water .
Human: what is the color of blood ?
Machine: it is the same as a black eye .
Human: what is the usual color of a leaf ?
Machine: it is a green one .
Human: what is the color of a yellow car ?
Machine: yellow .
Human: how much is two plus two ?
Machine: four .
Human: how much is ten minus two ?
Machine: seventy – two .
via The Future of Neural Network-based Chatbots and Intelligent Virtual Agents: A Neural Conversational Model.
I think this is an amazing quote, and says a lot about what’s driving content innovation these days… Especially as Buzzfeed hires a longtime PepsiCo marketing exec, Frank Cooper, to help them blow up their approach this week…
Anyway: another thought prompted by a throwaway Ellis tidbit in relation to the news that some brands (in this case, Ballantines Whisky) after having escaped the early 2000s gravitational well of “build it and they will come”, slingshotted their way past “build it where the people are” have now set a heading for “deploy fleeting structures of content on other peoples’ networks” by commissioning a digital magazine for Instagram. I’ll get to the point, though. Ellis says this: “Used to be that porn was the vanguard of any new comms technology shift. Now it’s advertising. Has been for a while. Look at where the infomercial people are going” and he’s not wrong.
–Dan Hon quoting Warren Ellis.
…my test for outsourcing human work to machines is this: any task that has an output or outcome which can be pre-stated or even guessed, should eventually be performed by a machine.
Humans should eventually be left to more or less exclusively deal with open-ended endeavors that generate new organic value (as opposed to efficiency derived value).
Alluding to Peter Drucker’s thinking, effectiveness should be a human pursuit, while efficiency should be delegated to machines.
White collar repetitive knowledge workers will be replaced by automation, just as robots replaced blue collar manufacturing workers. #sxsw
— Greg Swan (@gregswan) March 7, 2014