Hey! Be careful what you say or do: someone, or something, is probably watching you. Here's a few tips you should keep an eye on, according to our readers this past week.
How to deal with users who are trying to pick a (wordly) fight with your bots?
One of the biggest issues faced by a chatbot developer is how to deal with abusive visitors who enjoy cursing or talking about adult topics with your bot. How should you deal with these users? Ban them? Accept the abuse? Allow the bot to fight back?
Old pond, a frog jumps, the sound of water. Is Microsoft getting too soft? How about a softbot?
The AI’s goal once it sees an image is to generate a certain amount of lines using keywords it associates with contents of the picture. It generates these keywords by analyzing the image with GoogleNet, an AI algorithm developed by Google, and then separate algorithms to build the poem’s phrases word by word. Those keywords could be words like”rocks” or “tree.”
The game is rigged, and the bots know it.
OpenAI announced that they are working on improving OpenAI Five even more and that it will compete in “The International” — the biggest international Dota2 tournament, where teams can win millions of dollars. OpenAI Five will have a chance to become the champion of the famous Dota2 and to show again how much we have advanced Artificial Intelligence.
Let's figure out how to make those Facebook Messenger bots more powerful together.
To be clear, I am not just talking about displaying a website inside of Facebook Messenger. I am talking about using a web page that is built and designed to interact and enhance the Messenger experience.
What's going on here? Where are the boundaries that the AI should respect? Let's find out.
There were many predictions for chatbots, some of which came true, others… not so much. I’ve highlighted a few of the most common predictions here and added my own quick narrative as to whether or not those predictions came true.