Connection ErrorBad RequestThis page went staleSession ExpiredSign in requiredForbiddenNot FoundToo Many RequestsServer ErrorBad GatewayService UnavailableGateway TimeoutHTTP Version Not Supported
Session Expired
Your session has expired. Please log in to continue.
Sign in required
You need an account to do that. Sign in or create one — it only takes a minute.
This page went stale
Your security token was rejected, usually because the page sat open too long or you signed in elsewhere. Nothing was saved. Reload the page and try again.
Request Failed
We encountered an issue while processing your request.
Please check your internet connection and try again.
Yeah. The AI is really bad with context, but I'm not surprised. And it will never understand the nuances of local humor.
Actually, this is a tricky point.
When one interlocutor is joking and the other is being serious, which side should the AI take? How should such a dialogue be perceived — as humorous or serious? A rhetorical question.
Of course, a veteran moderator wouldn't have issued a warning for that. But their context is years of interaction with participants, not just the context of a single thread.
If you look at the recent messages — you were writing very bluntly, "head-on." As for Loken, I think the AI won't be able to find fault with him, because he conducts the dialogue more subtly and intricately.
Well yes, the style is different. I see that it's incapable of understanding who Mortulus is and that he's been discussing his growth for about 7 years. In short, the tool is good against spammers, but not against people.
Небо – мольбы не ждёт Небо – угроз не слышит Небо – ведёт особый счёт Небо – тебя найдёт