e7537d032e
The classifier learns models/seeds and the router is prompted with routeSystem, and they held different definitions on 80 lines. Sensor and host state was system in the seeds and is query in the prompt, which is the V-374 edit the seeds never received. World questions were chat, written before external search could answer them. 64/91 to 66/91 on the fixture. en-sys-002 and ru-query-011 gain, nothing regresses, clarify counts unchanged. The third disagreement is measured and rejected. Dropping the eight bare reminder verbs scores 65, because a centroid is a shape to be near and the bare verb phrase is part of that shape. A seed file and a prompt have different jobs there.
36 lines
1.0 KiB
Plaintext
36 lines
1.0 KiB
Plaintext
# chat.txt — conversational utterances routed to IntentChat.
|
||
# The chat intent captures free-form conversation that doesn't match
|
||
# any transactional intent (fact/reminder/note/query/act).
|
||
# The LLM replies from dialogue history + general knowledge.
|
||
что ты думаешь о жизни
|
||
расскажи что-нибудь интересное
|
||
как у тебя дела
|
||
как прошёл день
|
||
расскажи про себя
|
||
ты мне нравишься
|
||
о чём поговорим
|
||
у тебя есть чувства
|
||
расскажи историю
|
||
шутка
|
||
анекдот
|
||
пошути
|
||
привет
|
||
как дела
|
||
чем занимаешься
|
||
как настроение
|
||
что нового
|
||
думаешь о чём-то
|
||
расскажи про космос
|
||
что было интересного сегодня
|
||
как тебя зовут
|
||
сколько тебе лет
|
||
what do you think about
|
||
tell me something interesting
|
||
how are you
|
||
tell me a story
|
||
i'm bored
|
||
what's up
|
||
tell me a joke
|
||
do you have feelings
|
||
tell me about yourself
|