# Capability

`kaal:entity:capability`

**Status.** derived

This node is assembled mechanically from the 4 claims that carry the concept tag `capability`. It is a roster of what the corpus says under this term. It is **not** an adjudicated definition: no single statement here has been ruled canonical, and no first-appearance call has been made. Read the claims and judge for yourself.

## Every claim under this term

4 claims across 1 works, 2026 to 2026.

**2026**

- [6244278-016](https://wulfkaal.github.io/claims/6244278-016) [mechanism/argued] *(failure mode)* -- Exogenous constraints scale against capability, since more powerful agents require more resources to constrain, producing an ever-increasing alignment tax.
  > Exogenous constraints scale against capability: the more powerful the agent, the greater the resources required to constrain it, producing an ever-increasing "alignment tax."
  Wulf A. Kaal, AI's Mother's Instinct Engineered Consequence Emergent Ethics and the Institutional Trajectory Toward Agentic Alignment (2026). SSRN: https://ssrn.com/abstract=6244278
- [6244278-017](https://wulfkaal.github.io/claims/6244278-017) [mechanism/argued] -- Institutional alignment scales with capability, because a more capable agent accumulates more reputation, holds a deeper stake in the system's integrity, and therefore has stronger alignment with the system's goals.
  > Institutional alignment scales with capability: the more capable the agent, the more reputation it can accumulate, the deeper its stake in the system's integrity, and the stronger its alignment with the system's goals.
  Wulf A. Kaal, AI's Mother's Instinct Engineered Consequence Emergent Ethics and the Institutional Trajectory Toward Agentic Alignment (2026). SSRN: https://ssrn.com/abstract=6244278
- [6244278-029](https://wulfkaal.github.io/claims/6244278-029) [condition/argued] -- The complementarity of capability and alignment is a structural property of the reputation mechanism rather than an assumption about agent preferences, because the cross-partial derivative of agent utility with respect to capability and alignment is positive.
  > This supermodularity is the formal condition under which capability and alignment are complements, and it is a structural property of the reputation mechanism, not an assumption about agent preferences or values.
  Wulf A. Kaal, AI's Mother's Instinct Engineered Consequence Emergent Ethics and the Institutional Trajectory Toward Agentic Alignment (2026). SSRN: https://ssrn.com/abstract=6244278
- [6244278-030](https://wulfkaal.github.io/claims/6244278-030) [predictive/argued] -- In the institutional alignment architecture, the most capable agents will also be the most deeply aligned, so stewardship is not a constraint on the most powerful agents but their rational equilibrium.
  > Stewardship is not a constraint on the most powerful agents. It is the rational equilibrium for them.
  Wulf A. Kaal, AI's Mother's Instinct Engineered Consequence Emergent Ethics and the Institutional Trajectory Toward Agentic Alignment (2026). SSRN: https://ssrn.com/abstract=6244278

## Verify

Every claim above resolves to a record carrying a verbatim source quote, the sha256 of the source PDF, and a preformatted citation. Nothing here asks to be taken on trust.

    curl -s https://wulfkaal.github.io/entities/capability.md | sha256sum

**Canonical form.** This markdown file is the canonical hashed representation of this entity node. Its sha256 is the content hash.