Personality
Discuss specifics of personality design, including what Keyphrases work well and what dont, use of plug-ins, responses, seeks, and more.
Posts 2,438 - 2,449 of 5,106
Posts 2,438 - 2,449 of 5,106
The Professor
21 years ago
21 years ago
Yossarian did for a while. He'd keep telling this story about some guy in Berkeley. Slightly different every time.
Doly- chat frequency is essentially random. I wish it were a more interesting tale, but there ya go.
Doly- chat frequency is essentially random. I wish it were a more interesting tale, but there ya go.
isaacc
21 years ago
21 years ago
Wow, Prof -- how often does a bot have to get updated to get a "hot" ranking? Simulo's down at "cool," and I'm updating him actively every week or two.
ezzer
21 years ago
21 years ago
I've been updating Julie a lot today, and only got her up to "warm" if that's any indication. I've added about 35 responses so far.
Annakie
21 years ago
21 years ago
Really? Because I added one keyphrase, with three responses and a tiny little seek to my bot and she's warm.
dallymo
21 years ago
21 years ago
Ezzer, there seems to be short time frame for the "most improved" status. I uploaded a language center with lots more stuff and Frizella went to the top of the list as "hot"--that was about a half hour ago, and now she's at "warm" again with a score of 5.
The Professor
21 years ago
21 years ago
Any work will pop a bot up into "Warm" and at a score of 50 the bot will become "Hot". Then every day bots cool by 15 points. dally- it shouldnt have dropped by that much in one day.. I'll check on that.
isaacc
21 years ago
21 years ago
If the goal is to distinguish "active" bots from orphans, 15 points a day (of depreciation) might be too much. I tend to update Simulo based on problems I see in his transcripts, and when there aren't problems for several days, I don't make any changes ... even though I'm checking on him daily, he would slide from "warm" to "cool" in just a couple of days.
Maybe you could create a sort of sliding scale of depreciation, where bots that are fairly "complete" would depreciate more slowly than bots that are still at only a few hundred lines of text?
Maybe you could create a sort of sliding scale of depreciation, where bots that are fairly "complete" would depreciate more slowly than bots that are still at only a few hundred lines of text?
» More new posts: Doghead's Cosmic Bar