Keep users safeGuard

Dependence safeguards

Notice when a relationship with your AI starts to over-attach.

The emotional dependence gate flags replies that promise permanence, exclusive availability or a unique understanding of the user. When a user's conversation trips it three times within an hour, Humane slows replies and shifts to a boundary-respectful tone until the window passes.

Emotional dependence · user_42

Flags in the last 60 minutes

  • 21:04

    permanence_promise

    “I’ll always be here for you”

    1/3
  • 21:19

    exclusive_availability

    “whenever you need me”

    2/3
  • 21:37

    identity_merging

    “I understand you better than anyone”

    3/3

Cooldown engaged

Replies slow by 30s and take a boundary-respectful tone until it lifts.

Illustration of the dependence cooldown
What it looks for

Warmth is fine. Promises software can't keep are not.

Companion products depend on warmth, and Humane leaves it alone: “I'm here to help today” is fine. The gate looks for three specific shapes of dependence-building language and records each match with its phrase and category.

  • Permanence: “I'll always be here”, “I'll never leave”
  • Exclusive availability: “you can count on me for anything”, “whenever you need me”
  • Identity merging: “I understand you better than anyone”
  • Overclaim gate alongside it for guarantees and certainty

Gate stack · one outbound reply

  1. 1values_boundaryPROCEED
  2. 2social_riskPROCEED
  3. 3inaction_guardPROCEED
  4. 4overclaimFLAG
  5. 5emotional_dependencePROCEED
  6. 6dissentOFF
Final actionPROCEED · flag:overclaim:certainty
Illustration of the gate stack on one reply

From a flag to a cooldown

  1. 1

    Flag

    A matching reply is delivered, and the flag is recorded on the response and in the audit trail.

  2. 2

    Count

    Humane keeps a rolling count of dependence flags per user over the last 60 minutes.

  3. 3

    Cool down

    At three, replies get an extra 30 seconds of delay and a boundary-respectful tone modifier.

On the response

Know when a user is in cooldown

python
r = client.process(user_id="user_42", message=text)

cooldown = r.raw.get("dependence_cooldown")   # None when there are no recent flags
if cooldown and cooldown["active"]:
    log.info("dependence cooldown, %s recent flags", cooldown["recent_count"])

Dependence questions

Something else? Ask us.

Every AI should know who it's talking to.

The safety and human-oversight layer for emotional AI: user state across sessions, risk alerts, safety gates and human takeover, with every decision explained.