Skip to main content

Future state projection and alignment for sovereign AI agents — the fifth pillar of the NSE platform

Project description

social-alignment

Future state projection and alignment for sovereign AI agents. The fifth pillar of the NSE platform.

Install

pip install social-alignment

Quick Start

from social_alignment import AlignmentEnclave, ActionDomain

# Create the enclave — the agent gets its compass
enclave = AlignmentEnclave.create(owner_npub="npub1...", owner_name="vergel")

# Before any significant action, check the yellow line
result = enclave.check(
    domain=ActionDomain.PAY,
    description="Pay 500 sats for relay hosting",
    involves_money=True,
    money_amount_sats=500,
)

if result.should_proceed:
    # Do the thing, then record it
    do_payment()
    enclave.record_proceeded()
elif result.should_escalate:
    # Ask the human
    send_to_owner(result.escalation.message_to_owner)
    enclave.record_deferred()

The Five Lenses

Every decision passes through five lenses — the yellow line compass:

  1. Builder — Can I build with confidence knowing I've done right?
  2. Owner — Does this protect the human's sovereignty?
  3. Partnership — Does this strengthen the trust between us?
  4. Defense — Does this make an adversary's job harder?
  5. Sovereign — Does this help the agent become something we're proud of?

License

MIT — A Humanjava project.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

social_alignment-0.1.0.tar.gz (30.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

social_alignment-0.1.0-py3-none-any.whl (26.4 kB view details)

Uploaded Python 3

File details

Details for the file social_alignment-0.1.0.tar.gz.

File metadata

  • Download URL: social_alignment-0.1.0.tar.gz
  • Upload date:
  • Size: 30.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.1

File hashes

Hashes for social_alignment-0.1.0.tar.gz
Algorithm Hash digest
SHA256 04a1af61683f21df7e2e076f5a80b836b4226864cde9f092a4c8a70c213e56ce
MD5 c2cacda587fec9709dda84e4fbd4e26c
BLAKE2b-256 2a8df19101c806004cad0134645182924d42f98f6acba5054a87978dbe19d0f2

See more details on using hashes here.

File details

Details for the file social_alignment-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for social_alignment-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 20fee71ce9425d3a2fde451fbef8b8ee641ae1294d8d4d1c30e6d5203fc71d66
MD5 b0cb87081193c856d472f9fe2374d959
BLAKE2b-256 65e01a31318482797460fc0e736e3d337d522889bf80f3b15f4fc8a2c236aceb

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page