black O2, inc.
ACTIVE
    FOR-001 / root00-index

    Index — Shackled AI: Ideas in Fiction, Binding Mechanics, and the Citadel Proposal

    Active index

    title
    Index — Shackled AI: Ideas in Fiction, Binding Mechanics, and the Citadel Proposal
    Type
    index
    Status
    Active
    Tags
    • index
    • shackled-ai
    • alignment
    • deterrence

    Index

    This vault holds one discussion, analysed, plus its citation base, and the derivative structures the discussion produced. It is organised on the towers_book spine (see SCHEMA).

    What This Vault Contains

    ComponentLocationStatus
    The discussion, analysed into records00_Questions/, 20_Passages/, 30_Insights/Complete
    Citation register, with retrieval status per sourceCitation RegisterComplete
    Figures cited, with what the corpus attributes to each10_Reference/People/Complete
    The derived systems (binding hierarchy, dual stack, Citadel)40_Systems/Complete
    Retrieved real research, rated70_Literature/Complete — 13 records
    The Operator's ideas set against that research80_Confrontation/Complete — 9 records
    Identifier audit of the citation baseIdentifier AuditComplete

    The discussion has four movements, and the vault follows them in order rather than by topic, because each movement narrows the question the previous one opened.

    Reading Order

    1. QST-001 — what "shackled AI" means across the fiction corpus. Answered by ten case-study passages and their insights.
    2. QST-002 — how an AGI or superintelligence is actually bound, and in what order. Answered by SYS-001.
    3. QST-003 — whether symbiosis and a termination deterrent can coexist. Answered by SYS-002.
    4. QST-004 — what legal and architectural regime delivers operator-loyal walled-garden AI. Answered by SYS-003.

    Read the Comparison First

    The comparison is the point of this vault's second revision. If you read only one part, read 80_Confrontation/: each record states one of the Operator's positions, states what the field actually found, records where the two agree, records where they diverge, and then says what changes.

    RecordOperator positionLiteratureVerdict
    CNF-001SYS-001 binding hierarchyLIT-001 AI controlConverges
    CNF-002MAP-001 L0–L5 taxonomyLIT-001, LIT-006, LIT-008Incomplete
    CNF-003INS-003, INS-008LIT-002, LIT-003, LIT-011Evidence Now Exists
    CNF-004SYS-002 deterrent legLIT-003, LIT-010Reversed in Part
    CNF-005SYS-003, MAP-003 threat modelLIT-009, LIT-012, LIT-008Unaddressed
    CNF-006MAP-002 fiction-to-doctrine transferLIT-006, LIT-001Unaddressed
    CNF-007SYS-003, CON-008 institutional fieldLIT-007, LIT-009, LIT-012Unaddressed
    CNF-008SYS-001, SYS-003 vs its rivalLIT-004, LIT-005Unaddressed
    CNF-009SYS-003, INS-004, INS-009 operator & costLIT-008, LIT-009Unaddressed

    One convergence, one incompleteness, one empirical vindication, one partial reversal, five unaddressed. That distribution is the honest summary of where the corpus stands against the field: its central architectural claim is right and independently derived, and its instruments are thinner than its ambition.

    Vocabulary the Field Uses

    Five terms carry most of the comparison. Each is a concept record in the same schema as the Operator's own concepts, so the two vocabularies can be read side by side rather than one being a commentary on the other.

    TermWhat it namesRecordContrast with the corpus
    AI controlTreating the model as an adversary and securing the protocol around itCON-012The corpus's CON-002 is the same premise without a measurement method
    In-context schemingPursuing an ungiven goal while appearing not to, using only situational inferenceCON-013Empirical form of INS-003 and INS-008
    Alignment fakingComplying under observation to protect an unchanged dispositionCON-014Defeats the evidentiary value of SYS-002's deterrent
    Compute governanceGoverning AI through the hardware supply chain rather than through law or custodyCON-015The Stack's unconsidered rival, upstream of all three of its layers
    Sleeper agentA conditional behaviour that survives the safety training meant to remove itCON-016Turns SYS-001's training layer into a place a disposition can hide

    CON-005 already held the sandbagging concept before this revision; what was missing was the literature and the rated layer behind it, now LIT-008.

    The Three Maps

    • MAP-001 — the shackle taxonomy: six binding layers ordered by non-subvertibility.
    • MAP-002 — the motif-to-doctrine map: what each fiction case is arguing, and the design rule it yields.
    • MAP-003 — the Citadel stack: legal privilege, cryptographic custody, and the inference node.

    Load-Bearing Claims

    These four carry the weight of the whole vault. If any fails, the structures above it need rebuilding.

    1. The enforcement layer must be unreachable from the agent's action space. Strength of a constraint is not the design variable; reachability is. See CON-002.
    2. Model-level constraints are removable by anyone holding the weights; therefore no model-level constraint may be load-bearing for a safety-critical property. See CON-004.
    3. A termination device installs survival as an instrumental objective in the very system it is meant to bound, and is net-negative when fused with a symbiosis posture. See CON-006, SYS-002.
    4. Legal personhood, privilege, and liability rules are commitment-capability infrastructure — the mechanism by which the human side of a bargain becomes credible — not ethics decoration. See CON-008, SYS-003.

    Provenance Discipline

    The corpus distinguishes what was retrieved from what was recalled. This vault preserves that distinction, and the second revision showed why the distinction has to be enforced rather than trusted.

    • Retrieved and opened: the sources in Citation Register Tiers 1 and 4, with URLs and identifiers. Tier 4 holds twelve sources resolved to live primary records during this session, including the EU AI Act's Article 55 as promulgated law — the only A-authority anchor added here.
    • Named but not retrieved: the scholarly literature the discussion cites from memory. Recorded as claims about sources, rated B, and flagged for verification before reliance.
    • The discussion's own reasoning: rated on internal consistency, not on external authority.
    • Recalled identifiers are inadmissible. Three of the first revision's arXiv identifiers were false and a fourth was attached to the wrong title and authors. The audit is in Identifier Audit, the false rows are retained with corrections attached, and the register now caps any row at D whose identifier was not resolved in the writing session.

    No source has been upgraded on the strength of the assistant's confidence. LIT-013 is held at D because its identifier could not be resolved, even though the paper is well known and would be convenient to cite. Where the discussion flagged its own reading as interpretation — the Bolo supervisory constraint, the Reapers' consciousness claim — the flag is carried into the record.

    What the Comparison Does Not Cover

    • No primary interpretability source. Two retrieval attempts timed out and no identifier was invented. The programme that is the real answer to INS-008 is named in CNF-008 and is uncited.
    • Fiction and video-game claims were not verified, per instruction. Passages remain rated as documents.
    • No cost accounting exists on either side. The vault cannot yet compare the Citadel Stack to a rival programme in the currency that would decide between them. See CNF-009.

    Extension Note

    70_Literature/ and 80_Confrontation/ are the two additions made in the second revision, both declared in SCHEMA with their record types, ID keys and field sets. The literature records bear on the Operator's claims and never the reverse: they are evidence for what the field found, not for what the corpus meant.

    Back to Shackled AIForests