@abram

Frames owned

• abstraction-arc: Which work on abstraction, logical induction and agency gives the program a representation theorem for logical inductors, a decision theory set in that representation, and a notion of scale-free agency that covers cooperative equilibria?
• authorship-and-transparency: When is a verdict the principal's own program's and a channel's influence the declared reference on the declared inputs, and does the thick definition of legitimacy satisfy the thin specification?
• cooperative-equilibria-as-agents: Which characterization of approximate cooperative equilibria among learning agents as agents, with enforcement against an AI leaving the coalition, yields advice for steering toward them?
• ddb-to-li-translation: What does each result of Deference Done Better become when the novice and the expert are logical inductors?
• decision-theory: Which decision theory for computationally uncertain agents, on the updateless side and in the synthesis of logical induction with bounded inductive rationality, is tractable, and which of its results bear on AI safety engineering?
• deference-and-trust: Which research on trust between a human inductor and an AI inductor, at the logical-induction level, reaches a formal account of trust that guides AI safety engineering work?
• deference-finite-results: Which finite results about delegation, certificates, exposure, substitution, magnitude and corrective control does the deference line hold as kernel-checked theorems?
• deference-toward-bounded-agents: Does the deference collapse, or an analogue of it, hold for a bounded trained agent deferring to human teachers?
• enabling-work: Which repository infrastructure makes the trust research vettable and publishable?
• formalism-open-questions-0-3: Which of the open questions listed for the li-deference formalism yield to the legitimacy and trust work, and in what form?
• integrity-and-record: Can a cognitive trajectory falsify or silently rewrite its own normative history, and what does an Integrity evolution of the accounted obligation state conserve?
• inter-inductor-total-trust: Which pairs of a novice inductor and a distinct inductor expert satisfy Total Trust, and on what minimal conditions?
• ledger-logic-market-logic-synthesis: Which results of a ledger formulation and of Market Logic hold as one body of mathematics, and where do the two frameworks part?
• legit-dynamics-learning: Under what conditions does an AI learning the humans' concept of legitimacy learn enough of it to avoid wireheading and manipulation, and can legitimacy, once lost, be repaired?
• legitimacy: What must stay true of a trajectory's record, verdicts and channels of influence, inside it and at its boundary, for a later judgment to count as the principal's own, and what does corrigibility consume from that?
• legitimacy-meets-syntax: How does legitimacy cash out as local rules of sanity, and how do inferentialist semantics and map-territory semantics connect?
• legitimacy-reasons-programme: What makes a teaching or feedback channel legitimate, how does legitimacy enter the trust principles between a human process and an AI, and what does it owe to reasons and to inference?
• level-above-quantifiable: Which work at the level of probability frames and Jeffrey–Bolker models advances a formal theory of trust that guides AI safety engineering work?
• level-poly-time: Which whole-mind models of rationality at polynomial time or below would advance a formal theory of trust?
• level-super-turing: Which work at the limit-computable level of AIXI and reflective oracles advances a formal theory of trust that guides AI safety engineering work?
• li-deference-machine-checked: Which machine-checked statements over a formalized logical induction criterion establish the li-deference results as the prose states them?
• managing-misalignment-to-li: What do the results of the Managing Misalignment paper become when the novice and the expert are logical inductors?
• openness-and-non-capture: Can concerns reach a process at all, and can the party they matter to still act on them, on the actual branch and under every declared intervention?
• sams-conjecture-li: Can a fast epistemic process that the human inductor trusts be built from the AI inductor's forecasts of the human inductor's later beliefs?
• stage4-condensation-dynamics: Which notions of function and isomorphism, which role for the observables, and which dynamics of theories carry the same concept between agents and across ontological shifts?
• stage5-li-representation-theorem: Which abstraction of a logically uncertain belief state, and which simplicity argument, make it natural to interpret an observed system as a logical inductor?
• stage6-dt-and-scale-free-agency: Which decision theory, set in the Stage 5 object, and which notion of scale-free agency characterize approximate cooperative equilibria as agents, with advice for steering toward them?
• stance-and-level: Where should the program work: at which level of computability, under which decision-theoretic stance, and does the computationally unbounded level represent the phenomena that matter?
• the-program: How can a powerful AI develop in line with humanity's interests without relying on control — and how can we get mathematical guarantees that it does?
• updateless-dt-programme: Which decision theory for computationally uncertain agents on the updateless side is tractable, and which of its results bear on AI safety engineering?

Wants

None.

Events

No human event has touched this node.