• Using [] seems to work best.
  • Leave a space after the [, and after the ] (So: [ Mark words words ]).
• Be mindful about using {}, you might get unwanted associations with programming languages (Valahraban)

  the wiki people say {} is closer to the topic of programming/pure data and I'm inclined to agree

(also see corresponding section on the NAI wiki)

• '' for binding words together (Shincore): Use '...'. Asian/'Pacific Islander' for an Asian Pacific Islander, 'fully automated', 'first name last name', etc.
  • Note by Rinter:

  " [in AID] ' and _ had some overlapping use case, but generally ' was literal and _ was instructional. Literal in the sense that you're telling the AI to always write it this way, exactly.

• & still seems to work as 'and' for lists (basically a replacement of ","; as in CAT, etc.) (Noli, Shincore)
  • & appears to be a powerful list separator. The AI seems to use the list items more reliably in concise formats. Uncertain of value in full prose. (Kalmarr)
• () for giving specifics (RollForPanda): "I'm finding a lot of use for ( ) when describing something specific" (also see RollForPanda's Asari and Turian examples above for usage)
• ; might be a good seperator for categories / traits. Mainly because it was used this way to tag metadata in the fine-tune. (Kalmarr)

(various)
Capitalization matters! Words can be different tokens depending on how they are capitalized. In general you want to use lowercase variants of words for Lorebook entries, memory, A/N, stage instructions, etc. Simply because these should be the variant that the AI has the most training on and hence "understands" better. Exceptions are words where the capitalized variant is more common (names, countries , etc.). In some cases, meta-data tagging in the fine-tune can also make the capitalized variant more useful than the lowercase variant (Fantasy seems to get better results in A/N than fantasy for example). These exceptions have to be discovered through experimentation.