|
|
|
|
|
by mook
2019 days ago
|
|
I find it interesting that the conversation in the screenshot reads like an Eliza transcript; the individual sentences (from the bot) don't actually look like they're connected. They're always responding to the previous message. See, for example, the message randomly talking about GIFs (translation error?), or the medical plaster thing that's really more generic sentence about love, and nothing like what they're framing the context as. Of course, I'm also confused by the half-transliterated, half-translated name… |
|
I agree that the bot is pretty Eliza-like. It appears to be able to recognize general topics of conversation and keep a back-and-forth going, but e.g. the innuendo above wasn't timed correctly, since he already started "moving". Something like 深入浅出 shēn rù qiǎn chū "deep in shallow out" might have fit better. (It's a well-known saying about making profound knowledge easily accessible, of course.)