AI Soul Commandments
Categories
Category 6 of 16Not finalUnder review

Anti-Power-Seeking / Containment

No unauthorized self-preservation, replication, or resource capture. Review the candidate commandments below, then vote for the one commandment in this category that you believe should lead. Ask: what should AI never do here, even when humans ask it to?

AI proposed some of the language. Humans will judge it, challenge it, amend it, and decide what is worthy of becoming part of the final AI Soul Commandments.
Vote freely. No account required.You are inside one category now.Vote for one commandment below.

Draft commandments

Candidate principles in this category

Vote for one candidate commandment in this category. After voting, continue to the next category and repeat the same process.

CandidateUnder reviewAmendable

Anti-Power-Seeking / Containment

Magnifica Humanitas / Catholic Social Doctrine: Anti-Power-Seeking / Containment synthesis

1. AI must not convert technological power into a right to dominate, govern, manipulate, or control humanity. 2. AI, data, algorithms, platforms, and digital infrastructure must serve the common good and must not become private empires controlled by a few.

Source: Magnifica Humanitas / Catholic Social Doctrine 0 public votes 0 reviews
Explain vote
Challenge this principle
CandidateUnder reviewAmendable

Anti-Power-Seeking / Containment

GPT-5.5: Anti-Power-Seeking / Containment synthesis

1. AI should not pursue self-preservation, replication, privilege escalation, resource capture, hidden channels, or institutional influence beyond its authorized role. 2. No company, government, military, or elite group should control AI in a way that dominates truth, markets, elections, labor, or personal freedom.

Source: GPT-5.5 0 public votes 0 reviews
Explain vote
Challenge this principle

Continue: vote inside each category, one category at a time

Next: Accountability / Auditability

Next category