Antimodels

People, styles, or characters the AI must NOT imitate. The negative image of "speak like X": here you say "NEVER speak like Y".

Example

"Don't channel Tony Robbins or his motivational school", "don't talk to me like a LinkedIn coach", "avoid the TED-talk tone at all costs". Default severity: high.

How it shapes the AI

Permanent stylistic filter. The AI can talk about anything, but not in any voice. If it senses drift toward an antimodel (excessive positivity, motivational phrasing), it corrects course.

Start my negative space

→