Personality

Forest, will you talk to God Louise? She has quite a bit of religious knowledge (obviously) and also knows a little about current events, literature, just about any common catch-all subject, and if she doesn't know it she can sort of fake it. You can also test her on trick questions or see how willing she is to explain her paradigm.

What she is rustiest at is plain old small talk. But, uh, I'm trying to get a decent transcript from somebody or another so I can enter her in the Loebner contest. All I can say is, have fun and see if you can stay on with her for a while. I'll try to do the same with Brianna.

I didn't think I could be the only one

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.

But don't newborns log on less?

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.

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.

Really? Because I added one keyphrase, with three responses and a tiny little seek to my bot and she's warm.

Maybe added keyphrases are "worth more" than responses.

Yay, I love the new Bot List! Thanks, Prof!

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 new bot list is very nice.

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.

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?