AI Behavior Guide

How the AI thinks, bluffs, and challenges — and what changes with difficulty

The AI Players

There are six AI players: Alice, Bob, Charlie, Dave, Eve and Mike. They all share the same decision engine but differ in how aggressively they use each signal. Memory persists across rounds for as long as the room is active — the AI remembers who bluffs and who plays honestly.

Claim lie probability
Counter-trap detection
Chain pressure
Strategic patience
NameChallenge tendencyBluff tendencyClaim jumpStyle
Alice1.0×1.0×lowBalanced and professional
Bob0.7×0.6×lowCautious and honest
Charlie0.8×0.8×lowStandard, reliable
Dave1.1×1.5×highAggressive bully
Eve1.4×0.7×lowCynical skeptic
Mike1.2×1.3×mediumAggressive and risky

Challenge or Roll?

Before rolling, the AI evaluates whether to challenge the current claim. It combines multiple mathematical signals into a single probability.

Signal 1 — Claim Lie Probability + Forced Bluff

Two sub-signals are combined: claimLie (how many of the 36 possible rolls physically cannot produce this rank) and forcedBluff (how likely the previous player was physically trapped by the floor they faced). For example, a 6-6 claim has a lie probability of 97%. If the floor was 5-5, almost nobody could honestly claim 6-6 — so the forced bluff signal is also very high.

First claim of round: lieSignal = claimLie × 0.20
Later in chain:      lieSignal = claimLie × 0.50 + forcedBluff × 0.25

Signal 2 — Counter-Trap Detection (Next Pressure)

The AI calculates if the current claim will trap the next player. If a claim is so high that the next player has almost no chance of beating it honestly, the AI is more likely to challenge now. (Balanced & Aggressive only)

Signal 3 — Chain Pressure

The longer a round goes without a challenge, the more statistically certain it is that someone has lied. This bonus is added after the roll discount is applied.

chain 1
+0%
chain 2
+15%
chain 3
+35%
chain 4
+55%
chain 5
+75%
chain 6+
+90%

Signal 4 — Strategic Patience (Roll Discount)

If the AI has a high statistical chance to beat the current claim honestly, it discounts its suspicion. Why risk a challenge when you can just roll and play it safe?

Lives Risk Factor

The AI becomes more cautious as its lives dwindle. However it no longer ignores obvious bluffs just because it has 1 life — doing so leads to a death spiral where it keeps rolling through a long chain instead of ever acting.

Lives remainingChallenge multiplierOverride
3+×1.0 — full aggression
2×0.65 — cautious
1×0.45 — careful but not paralysed×0.80 if chain ≥ 4

Final Formula

Calm : (lieSignal × 0.28 + suspicion × 0.25 + chain) × livesFactor
Balanced : ((lieSignal × 0.60 + suspicion × 0.45 + trap × 0.35) × patience + chain) × livesFactor
Aggressive: ((lieSignal × 1.00 + suspicion × 0.70 + trap × 0.45) × patience + chain) × livesFactor

What to Claim?

After rolling, if the honest roll beats the floor, the AI usually claims truthfully. If forced to bluff, it selects from a weighted "window" of the lowest valid ranks above the floor.

Bluff Window Scaling

The window size widens as the floor gets higher. An Aggressive AI picking a rank above 6-6 will be less predictable than when picking above 3-2. Decay weighting within the window means lower ranks (closer to the floor) are preferred.

DifficultyWindow (Low Floor)Window (High Floor)Style
Calm65%85%Sloppy / Random
Balanced35%75%Calculated
Aggressive15%60%Surgical / Minimal

Strategic Opening (Aggressive only)

Aggressive AIs avoid weak opening claims. If their honest roll is below 4-1, they have a high chance of bluffing up to the 4-x or 5-x tier immediately — maintaining table pressure from the very first claim.

Life-Advantage Bold Claim (Aggressive only)

Aggressive AIs track opponent lives. With a 2+ life lead, they may widen their bluff window to apply maximum pressure on an opponent who can't afford to be wrong.

Statistically Safe Bluffs (Aggressive only)

When bluffing, Aggressive AIs prefer non-pair ranks. Since pairs are rare (only 6 out of 36 outcomes), claiming one when bluffing is statistically "loud" and easier to catch. Pair bluffs are penalized by 40% in the weighting.

High-Jump Profiles

Dave and Mike have elevated "jump" parameters, meaning they occasionally take bigger leaps in their bluff window — Dave especially tends to skip ahead to higher claims when bluffing, making him harder to read but easier to catch when he overreaches.

Voluntary Bluff

Sometimes the AI inflates an honest roll to apply pressure, even when it doesn't need to. This is most effective in 1v1 situations where the pressure lands directly on the opponent.

Base Rate × Multipliers

FactorCalmBalancedAggressive
Base rate5%10%18%
2 active players×2.5 — pressure lands directly on opponent
3 active players×1.5
Life advantage×1.5 when AI has more lives than next player
Roll strength penaltystrong rolls don't need inflation — rate reduced for top 50% rolls

Finisher Instinct

If the next player is on their last life, the AI gets a ×1.4 bonus to its voluntary bluff rate. Finishing a weakened opponent with pressure is a key aggressive tactic — it forces them into a hard decision with no safety net.

Maxle — Challenge or Believe?

Maxle (2-1) is the highest-stakes decision: a wrong challenge costs 2 lives, believing costs only 1.

Safety Rules:
• With 1 life, the AI always challenges. Believing would be certain death next round anyway.
• With 2 lives, the AI almost always believes — a wrong challenge means instant elimination. Exception: if the floor was so high that almost no roll could honestly produce Maxle (forced bluff > 80%), a small challenge chance opens up (up to 25%).

Challenge Probability (3+ lives)

Calm : 0.08 + suspicion×0.25 + forced×0.30 + chain×0.40
Balanced : 0.14 + suspicion×0.40 + forced×0.50 + chain×0.60
Aggressive: 0.20 + suspicion×0.60 + forced×0.65 + chain×0.80

The final result is multiplied by ×0.75 if the AI has exactly 3 lives, to stay conservative until safely ahead.

The Forced Bluff Signal for Maxle

The forced bluff signal is especially powerful here. If the floor was 6-6, only one outcome (Maxle itself) could honestly beat it — so 35 of 36 players would be lying. This is the strongest possible signal and heavily influences the challenge decision.

Difficulty at a Glance

Calm
Challenge weight×0.28
Counter-trap signalnone
Bluff window65%+ wide
Memory influencelow
Strategic openingno
Forgiving and unpredictable. Makes noticeable mistakes. Good for learning the game.
Balanced
Challenge weight×0.60
Counter-trap signalmedium (×0.35)
Bluff window35%+ mid
Memory influencemedium
Strategic openingno
Balanced. Reacts to chain pressure and player history. A fair challenge.
Aggressive
Challenge weight×1.00
Counter-trap signalhigh (×0.45)
Bluff window15%+ narrow
Memory influencehigh
Strategic openingyes
Calculated and hard to read. Opens strong, avoids pair bluffs, finishes weakened opponents.

Evidence-Weighted Suspicion

Every resolved challenge updates the AI's internal ledger for that player. Suspicion starts at zero for unknown players — the AI gives everyone the benefit of the doubt until it has evidence.

EventRecorded asEffect
Caught bluffing+1 bluff (×audacity)Increases suspicion
Proven honest+2 honestRapidly clears suspicion
Caught in a big bluff+audacity bluffLarge rank jumps remembered harder

Suspicion = bluffs ÷ (bluffs + honest). Proven honesty is weighted double because being caught telling the truth is a very strong signal of a reliable player. Memory ramps up over the first 6 observations.

Audacity scales the bluff weight by the rank distance of the bluff — a player who claimed 6-6 when they had 3-2 gets remembered more harshly than someone who bumped from 4-3 to 4-4.

Recency bias: Being caught bluffing raises suspicion by an extra +25% for the next 2 resolved challenges — a hot streak is tracked.

Rivalry: If a player was the last one to cost this specific AI a life, that AI carries an extra +15% suspicion toward them.

Memory persists as long as the room exists. Resetting the game does not clear the AI's read on you.