Slowly but surely Cleverbot bypasses Suzette
Not so long ago, in 2010, the Suzette chat bot won the Löbner prize as part of the Turing test. However, competitors are not asleep!
Not so long ago, in India, the Techniche festival was held, at which the Cleverbot chat bot made great strides, in fact, passing the Turing test. The test was conducted as follows: people chatted with people and the bot. As a result, 63% of the respondents took the people as people, and Cleverbot - 59%. If we consider that for passing the Turing test is considered a result of 50% or higher, then we can say that this is a victory!
After a brief conversation, this little thing was almost able to convince me that the bot is me, not he :)
')
The more a bot communicates with people - the smarter it becomes, increasing its “intellectual power” daily:
The only serious problem, in my opinion, in modern bots is the inability to maintain one theme throughout a long conversation. But with the pace that has been observed recently in the field of their development, I think that this is not far away.
The second problem, but already more general, is the Turing test itself. It is beginning to become obsolete. Raising the bar in it no longer makes sense, otherwise the people themselves will not be able to pass it. It is time to change something and create a new chat-bots evaluation system.
Not so long ago, in India, the Techniche festival was held, at which the Cleverbot chat bot made great strides, in fact, passing the Turing test. The test was conducted as follows: people chatted with people and the bot. As a result, 63% of the respondents took the people as people, and Cleverbot - 59%. If we consider that for passing the Turing test is considered a result of 50% or higher, then we can say that this is a victory!
After a brief conversation, this little thing was almost able to convince me that the bot is me, not he :)
')
The more a bot communicates with people - the smarter it becomes, increasing its “intellectual power” daily:
The only serious problem, in my opinion, in modern bots is the inability to maintain one theme throughout a long conversation. But with the pace that has been observed recently in the field of their development, I think that this is not far away.
The second problem, but already more general, is the Turing test itself. It is beginning to become obsolete. Raising the bar in it no longer makes sense, otherwise the people themselves will not be able to pass it. It is time to change something and create a new chat-bots evaluation system.
Source: https://habr.com/ru/post/132730/
All Articles