Hacker News Reader

> you'll need to make a chatbot that is indistinguisable from a human over video chat

This may sound cynical, but if you could arrange a tableau, looking like someone is paralyzed in a hospital environment, speaking like Stephen Hawking, then you don't need any serious advances in robotics (IIRC uncanny valley still hasn't been crossed) to fool humans. But I imagine the rules won't allow that.

View on HN

This is a good point, and arguably a weakness in the Turing test, the headline grabbing Eugene Goostman chatbot's limited success was from a similar "social engineering" style technique, of tying slowly, changing the subject, telling its own stories and claiming to be a distracted teenager with poor English.

In response to the comment by Coincoin, each judge gets to pick "Human, Computer, Not Sure" for both participants, so they're at liberty to respond "Human, Human". It's true that the "real" human might make someone more likely to declare the "fake tableau" a chatbot, but the perceived disability might also make them less likely to risk declaring them a computer.

Don't forget you are directly competing against a human. If you are a judge, which one would you chose? The still frame with a robot voice pretending to be Hawking or the actual human?

Reply on news.ycombinator.com