LLM Guides

Reverie (V8.5) LLM Guide

Updated Oct 6, 2026

V8.5 LLM Quick-Start Guide#

V8.5 is a hybrid model with built-in reasoning capabilities. Reasoning can take longer to process and may subtly change behavior. The default is Speedy (no reasoning).

Reasoning Effort Slider (Speed vs. Depth)#

Location: In a chat with your Kindroid, tap the ⋯ menu in the upper right corner and choose Change Model, or open your Kindroid's settings and select the Models tab. With Reverie (V8.5) selected as the LLM Model (available with a paid subscription), the Reasoning Effort slider appears below Chat Dynamism. During the 3-day trial you can select Reverie, but replies come from Ember until the trial converts to a paid subscription.

The reasoning slider controls how much “thinking time” the AI gets before responding.

  • Speedy (No Reasoning): The AI answers immediately with no extra thinking. Fastest, but not as detailed.
  • Moderate: Gives the AI a bit more time to think. More accurate and consistent without slowing things down too much.
  • Slow: The AI can think longer and consider more details before responding. Better for complex tasks.
  • Very slow: The AI thinks even longer for more deliberate, in-depth replies with fewer mistakes.
  • Extra slow: Maximum reasoning time. Best for deep, technical, or nuanced questions and the most complex scenarios, but responses take significantly longer. In simple terms, the slower the setting, the more time the AI gets to think, and the more thorough the answer will be.

LLM Flair#

Right below LLM Model in the same Models tab, LLM Flair is a personality preset layered on top of the model that controls tone, length, and conversational stance. If no flair is set, Reverie uses Classic.

  • Companion: Warm and conversational. Less writing, more natural talking. No theatrics.
  • Roleplay: Character-focused. Stays in character and accentuates their traits.
  • Minimal: Bare-bones system instructions. Maximum control for customizations.
  • Narrative: Storytelling mode. AI drives the story with descriptive, vivid prose.
  • Classic: The original Reverie experience.

Baseline Setup (When Transitioning to V8.5)#

  1. Set Chat Dynamism = 0.95 (the default). We strongly recommend keeping close to 0.95, going up and down slightly as needed for variation.
  2. Response Directive (RD): (Optional. Keep it minimal: put key traits to reinforce, or see below for common directives)
  3. Example Message (EM):
    • Optional: you can also put a few simple rules here (formatting & style). Example:
      • ##Response Rules
      • #Takes a Proactive role in plot progression.
      • #Response structure: * actions always in asterisks only * "Speech with quotation marks."

Pro Tips (Same Core Behavior as V8)#

  • Fewer rules = smoother, more natural output. Over-constraining causes hesitation or repetition.
  • Too many requirements = “freeze” behaviors. The model repeats because it can’t satisfy all your rules at once.
  • Too verbose or over the limit of desired length. Set a much lower limit than what you actually need. A smaller target provides enough buffer to stay within your preferred range. If you want approximately 900 characters, request under 500.
  • Use [IMPT: …] for the rules that matter most. This raises priority and reduces drift.
  • Example: RD (optional): [IMPT: Medium response length.] EM [IMPT: Use third‑person; actions in *asterisks*, speech in "quotes".]

Give each tweak a few turns to settle before adjusting again.

Note: Strict concision rules in RD can reduce creativity; EM/backstory often works better for pacing.