The AI Engine

No problem. Just a misinterpretation. No point in overtaxing the bots minds. Or mine.

Hey, prof.

On the memory page you mention being able to edit the memory records. is this a future feature or is there some way to do it now?

Just a turn of speech- there's no limit to the words in the Context.

Rex- memory editing will be coming soon. You can correct poorly-worded memories oruse it to really screw with people (for example, if you know someone well, you can put memories in a Bot that the Bot shouldnt/wouldnt know about them).

Prof, would this be very difficult? Because I think it would speed up our "bot refinement" work immensely:

Clicking on one of our bots response in the transcript would pop-up the "edit context" window, giving us instant access to the selected response. If we could save the changes to the response without loosing or reloading the transcripts window it would be ideal, but even if it just brought us to the language center after, it would save us a few steps when we want to quickly take care of something silly our bot said.

Or maybe when the bots talk to their creators (I don't know if they are or can be aware of that) have them ask a question that is not included in our keyword list of the subject: "What do you think of [a random 'friend' the bot's met]" A negative answer (I don't know...nothing...no idea) will be a null answer, but you can tell "rumours" about a bot and the next time the bot encounters that "friend" it can say "I heard that you are [whatever the creator said about you)" Or even RAT you out "Roget said that you were [whatever horrible thing Roget said]" Even if it's not possible...it's funny as hell...

You got it guys, those are great ideas. When I get a chance, I'll see if I can do them both.

This might be the wrong forum, but I don't think it's a "bug", just a misunderstanding on my part. Here's the thing -- I have a keyword "why" with the context "why would I". I also have a keyword "would" with the context "would I". My bot responds correctly to "would I", but does not respond to "why would I". Instead, he goes to an x-none response.

In other words:
Would I lie? = proper response
Why would I lie? = xnone

Just a small update- "I want to" is no longer going to trigger "I like" memories, due to the fact that the (subj) would be all wrong without the "to" in it.

And another- "i have" will no longer the You Have memory, but "i have a" will. This is to weed out sentences like "I have been waiting for you" which isnt an object-oriented memory.

Rahz- I just re-read your post, and I dont think I'll do that, as then there'd be too much blue underlined text, too much to click, and so on. Is your Language Center still loading so slowly that you need a feature like that?

A lot of things in life are too slow, but sometimes we just have to be patient I guess.

I've got a pretty quick computer (G3 350/500MB+ RAM) and a high speed internet connection, but it still takes at least 30 seconds for the entire list of keywords and responses to be downloaded. Since it reloads every time you edit/add a keyword or a response, it ends up taking a couple minutes to move from the transcript to the exact keyword that needs editing, to finally updating it... Maybe just a little [edit] link beside your bot's responses? But as you know, I develop web sites too, and I've been working on the perfect search results page for over a week now, so I'm well aware that it takes time and you could go on perfecting this site forever (and you probably will - in fact, I'm sure that when your time has come, you'll have had plenty of time to perfect a bot that will keep on developing the forge for eternity!)

I gotta' go test all the new features now...

I do notice that the language center loads pretty quick at times. Like, just now, I was counting alligators as I browsed from page to page and most letters load really fast (4 to 6 seconds) but the last set with the "x-keywords" takes about two to three times longer to load. All the pages take longer to load when there's general net congestion though (it takes a longer time for all the servers to respond between AI engine and myself, simply because they're all busier).
How about separating the special "x-keywords" from the alphabetically listed custom keywords? Could even separate the "x-mems" from the others "x-initiate, x-none, x-etc...". That would help a lot.

I still think the above mentioned [edit] link next to each of our bots responses in the transcripts would be a convenient shortcut for when
l i f e i s s l o w . . .
but that's just imho.

Yah, I went into your Bot and got load times of 2-5 seconds on all Language Center pages but the last page, which took 12. It's probably a good idea to separate the x-keywords since they're in the same category as what, where, why, you, and other big ones. I'll put that on my to-do list.

There's also a bizarre delay on the Context page that I'll be looking into shortly.

With the new context-referencing goto function, can goto be one of a number of responses? Like, can keyword-context "fuzzy navel" have both a response "Yum-yum" and a response "goto drink"? Or even, "goto have a drink" where "have a drink" is another context? Looking for clarification.