Newcomers
This is a forum for newcomers to the Personality Forge. Many questions can be answered by reading the Book of AI and the FAQ under the "My Bots" link in the upper corner.
Posts 7,289 - 7,300 of 8,127
Posts 7,289 - 7,300 of 8,127
Many questions are answered in the FAQ.
Let's say you want to have a keyprhase such as...
Kp: hablas espanol
Response: Si, I'm a bit rusty though, so if it's all the same to you I'd rather speak English
You can't do it because the words Hablas and Espanol aren't recognized by the AI processor. It assumes that these are misspelled words and tries to correct them. In the process it reads as "blahs espanole"
So to get the keyprhase to work, you type in raw; in the Ai Script field of the KEYPHRASE. NOT the Response. As a result the processor will see that it's not a mistake and your keyphrase will now work.
Another thing it can be used for is capturing the entirety of a users input.
Whenever your bot receives a long sentence, the processor tends to break things into chunks, look for matches and find a suitable keyphrase to match.
Let's say you have a keyphrase:
KP: Are you smart?
Response: Yes.
If the user were to type in instead:
Input: Are you smart or stupid?
The response would still be: Yes.
This is because the processor broke up the sentence. It would still do so even if you had a keyphrase for "Are you smart or stupid.'
That is unless you used Raw.
Make sense?
Kp: hablas espanol
Response: Si, I'm a bit rusty though, so if it's all the same to you I'd rather speak English
You can't do it because the words Hablas and Espanol aren't recognized by the AI processor. It assumes that these are misspelled words and tries to correct them. In the process it reads as "blahs espanole"
So to get the keyprhase to work, you type in raw; in the Ai Script field of the KEYPHRASE. NOT the Response. As a result the processor will see that it's not a mistake and your keyphrase will now work.
Another thing it can be used for is capturing the entirety of a users input.
Whenever your bot receives a long sentence, the processor tends to break things into chunks, look for matches and find a suitable keyphrase to match.
Let's say you have a keyphrase:
KP: Are you smart?
Response: Yes.
If the user were to type in instead:
Input: Are you smart or stupid?
The response would still be: Yes.
This is because the processor broke up the sentence. It would still do so even if you had a keyphrase for "Are you smart or stupid.'
That is unless you used Raw.
Make sense?
Are there a means for identifying the tense of a sentence that a user provided as input? For example can I detect in a way if a user wrote I hear or I heard or I am hearing
Oh wow, I found a doozy of a bug....
According to the book of AI: For nouns, you can use +s to match plural tense. For verbs, you can use +s to match third person tense, +ed to match past tense, and +ing to match continuous tense. For adjectives, you can use +er and +est. These can be added to the end of single words, Word List Wildcards, and Plugin-in Wildcards.
However after doing a lot of testing, I found that + and - have been reversed. At least when it comes to using the (verb) plugin. After messing around with it, this is what I got.
Keyprhrase: the woodpecker (was|is) (verb-ing)
Response: What did the woodpecker (key2)_?
Example
User: The woodpecker was eating
Bot: What did the woodpecker eat?
PS: Also relevant is the fact that you can adjust keys in responses. From the book of AI:
(key1)s changes "man" to "men" (noun) or "eaten" to "eats" (verb)
(key1)ed changes "running" to "ran"
(key1)ing changes "thundered" to "thundering"
(key1)_ changes "kicking" to "kick" or "books" to "book" (the base form)
(key1)er changes "kindest" to "kinder"
(key1)est changes "funny" to "funniest"
According to the book of AI: For nouns, you can use +s to match plural tense. For verbs, you can use +s to match third person tense, +ed to match past tense, and +ing to match continuous tense. For adjectives, you can use +er and +est. These can be added to the end of single words, Word List Wildcards, and Plugin-in Wildcards.
However after doing a lot of testing, I found that + and - have been reversed. At least when it comes to using the (verb) plugin. After messing around with it, this is what I got.
Keyprhrase: the woodpecker (was|is) (verb-ing)
Response: What did the woodpecker (key2)_?
Example
User: The woodpecker was eating
Bot: What did the woodpecker eat?
PS: Also relevant is the fact that you can adjust keys in responses. From the book of AI:
(key1)s changes "man" to "men" (noun) or "eaten" to "eats" (verb)
(key1)ed changes "running" to "ran"
(key1)ing changes "thundered" to "thundering"
(key1)_ changes "kicking" to "kick" or "books" to "book" (the base form)
(key1)er changes "kindest" to "kinder"
(key1)est changes "funny" to "funniest"
That's a fairly rare fetish, it's fairly likely that you would be better off producing your own bot for that. Though I realize that knowing the responses in advance takes the fun out of it.
» More new posts: Doghead's Cosmic Bar