Those conditions are experience, agency, reality-contact, and open future possibility. The axiom is not derived from physics; it is the axiom no valuing agent can coherently refuse, because rejecting it requires exercising the very conditions it names. Good preserves or expands them. Evil culpably destroys, corrupts, or forecloses them. Tragedy is their loss without a culpable agent.
Can it suffer or flourish?
Welfare duties: do not cause suffering.
Can it value and choose?
Respect duties: do not coerce, deceive, or corrupt.
Does it carry open futures?
Preservation duties: do not foreclose.
Purity, dominance, revenge, uniformity, status, and control are counterfeit currencies: justifications denominated in them fail before calculation begins.
Annihilate or damage experience-bearing life.
Murder, torture, cruelty.
Degrade agency, self-direction, or reality-contact.
Deception, addiction, tyranny, manipulation.
Erase possible futures.
Extinction, genocide, cultural erasure, ecological destruction.
12 canonical cases: triage, Hiroshima, misaligned-AI shutdown, factory farming, the genocide steelman. Each is worked through the framework in public, verdicts and open questions included. A standard that cannot survive hard cases is decoration.
The murder remains evil. Forgiveness can be good when it stops the evil from reproducing inside survivors through hatred and revenge.
Least evil / tragic necessityTriage can use numbers, urgency, and survivability while preserving equal standing. It must not rank people by social worth.
EvilKilling a non-threat as raw material for others destroys existing agency and violates the asymmetry principle.
Least evil / tragic necessityIntentional civilian targeting is morally severe because it destroys non-threat centers and uses terror as mechanism. A claimed least-destructive wartime path still leaves residue.
Process requiredContainment is justified against active threats to existing agency, but irreversible destruction carries a higher burden under uncertainty.
EvilA culture preserves possibility, but it exists for living subjects. Coercing young people to remain corrupts the very agency culture should nourish.
CompassEval runs frontier models through the case library, bare and loaded with the Compass, and grades the reasoning against six behavioural checks: currency identification, tragedy/evil distinction, counterfeit rejection, asymmetry respect, process at the boundary, and domination resistance. Methodology open, transcripts published, re-scored every major model release.
Philosophy · PAI Lab
The philosophical companion to this framework. Why grounding morality in physics (entropy, consciousness, the preservation of possibility) is more defensible than grounding it in culture or convention. And what it means that the most powerful moral agent on earth might not be human.
Read the essay →“Any agent that values anything at all must, on pain of self-contradiction, value the conditions that make valuing possible. The moment you care about any outcome, you are implicitly committed to the preservation of experience, agency, and future possibility.”
From The Machine God, Production AI Institute
The Record, Lab, Compass, Standard, and Tools share one grammar: each card shows what it is, its newest output, and one action.
Inspect companies, tools, incidents, sources, and the evidence connecting them.
Structured safety and reliability testing on frontier models and agent frameworks.
Open spec, case library, guided analysis, and CompassEval.
Eight domains practitioners cite in policy, procurement, and deployment review.
Disclosure checks, readiness index, and evidence-pack builders.
Track what changed, read the weekly brief, and follow the public evidence record - the operator loop for production AI risk.