Nieman Foundation at Harvard
HOME
          
LATEST STORY
Why “Sorry, I don’t know” is sometimes the best answer: The Washington Post’s technology chief on its first AI chatbot
ABOUT                    SUBSCRIBE
March 3, 2014, 12:38 p.m.
LINK: docs.google.com  ➚   |   Posted by: Caroline O'Donovan   |   March 3, 2014

I am newly returned from Baltimore and the NICAR conference, where one of the most laugh-out-loud sessions of the weekend involved Brian Abelson, Joe Kokenge and Abraham Epton talking about how and why to build Twitter bots. Stephen Suen, of MIT’s Comparative Media Studies writing program, has a helpful blog post about the conversation.

Kokenge laid out the basics of making a bot. Epton talked about his ILCampaignCash, a Chicago Tribune product that tracks and tweets campaign donations. Abelson offered a long list of bots both humorous (like @FloridaMan or @Haikugrams) and practical (like @TreasuryIO or @YourRepsOnGuns) that suggested the breadth of possibility when it comes to bots. There are also, of course, challenges:

Brian says the logic behind the Twitter bot is strict rather than greedy. He also points to issues faced with Times Haiku. “The challenge is, how are we not going to make a haiku of the Syrian civil war, how are we not going to make a haiku of something that’s serious… that’s why it’s easier to do some of these funny artistic ones rather than something you can put the name of a newsroom on.”

Once again, rate limiting is brought up — Abraham says you can write the logic of your bot to avoid having your account get deleted. “Use common sense,” he says. The more you avoid behaviors that make your bot seem like a spam bot, the safer your account will be. Joe and Brian agree — the rate limit is high enough that you can get away with a tweet every 5 minutes without hitting it.

Show tags
 
Join the 60,000 who get the freshest future-of-journalism news in our daily email.
Why “Sorry, I don’t know” is sometimes the best answer: The Washington Post’s technology chief on its first AI chatbot
“For Google, that might be failure mode…but for us, that is success,” says the Post’s Vineet Khosla
Browser cookies, as unkillable as cockroaches, won’t be leaving Google Chrome after all
Google — which planned to block third-party cookies in 2022, then 2023, then 2024, then 2025 — now says it won’t block them after all. A big win for adtech, but what about publishers?
Would you pay to be able to quit TikTok and Instagram? You’d be surprised how many would
“The relationship he has uncovered is more like the co-dependence seen in a destructive relationship, or the way we relate to addictive products such as tobacco that we know are doing us harm.”