Self-improving systems

Type: kb/types/tag-readme.md

Selective head: the membership definition, the update architectures, and the four-part pathway profile, with the load-bearing note per claim. Full tag membership comes from the by-tag sweep (kb/reference/navigation.md).

Membership

A self-improving system makes operative, evidence-responsive changes to its own behavior-determining organization. Read every attribution against a declared frame of boundary, horizon, and objective: including maintainers can make a development system a human-inclusive member, and self-improvement is relative to a declared objective — indexed in the attribution, antecedent in the pathway. When the objective itself changes, the change is improvement only against a level outside it. Below the objective sits the target level, where a structural property is pursued because it is held to serve the objective and is checked for achievement rather than for warrant — the profile dimensions below are read that way whenever they are treated as goals. Membership settles only the category.

Update architecture

Evidence may directly determine an update that is always adopted, as gradients and viability triggers do, or flow through the proposal-selection subtype, where search, reject-capable evaluation, and operative retention let a candidate be rejected first — and where false-positive acceptance becomes operative. A pathway may compose both.

Pathway profile

After membership and update architecture, profile the pathway across four parts rather than placing it on a ladder. The profile is descriptive and selects no order by itself; any comparison between pathways is indexed to a declared objective.

• Reflective structure — coverage of represented aspects and forms, plus the separate addressability profile over retained commitments.
• Improvement dynamics — cumulativity: later dependence through the retained result; accumulation versus compounding, with compounding tested in later improvement.
• Governance — what the methodology settles, and which of those decisions are warranted.
• Actor allocation — human, computational, or joint per function; allocation carries the comparison, and computational closure is its no-human endpoint, not a grade of reflectivity.

The four do not determine, subsume, or form a monotone progression through one another: each property's note states the entailments it does not license, and the placements below show which combinations actually occur. That is non-entailment, not full independence — coverage is structurally required for some addressability operations, and explicit criteria are what carry a decision to a computational actor.

What reflection adds

A self-improving pathway is reflective when it routes objective-bearing evidence into a change to the system's behavior-determining organization through a causally connected self-representation; later operation must depend on that change. This causal structure permits direct updates, proposal selection, and compositions of both. Authority family — evidence, advice, instruction, enforcement — does not decide reflection.

• Reflection buys addressability — retention later rounds can read, criticize, and selectively revise.
• Repeatable operative revision — complete addressability covers governing machinery; continuity keeps its revision path usable.
• Reflection makes retained lessons second-order — an addressable lesson can reject or rescope a represented prior commitment.
• Retrieval misses are path-local — a lesson cannot shape a task that does not surface it.
• Payoff hypotheses, still open: theory-mediated sample efficiency, and selective revision needing a faithful rationale.

Governance and computational allocation

• Methodological and computational closure track different changes — settled method can be human-executed; an unattended model can improvise.
• Computationally directed self-improvement is a fixed-boundary reallocation ending in contraction — the transition worth studying is intra-category, and its endpoint is whether the boundary can be contracted to exclude the humans.
• Increasing computational autonomy relocates human effort to the frontier — measure improvements per human judgment, not hours.
• Only explicit retention is durable, writable, and addressable — no tacit channel carries settled methodology.

Placements

Evidence: Commonplace paths show broad addressability; completeness remains open. Six external paths map supplied machinery; thirteen cases map profile combinations. Payoff remains untested.

Base vocabulary and boundary cases

• Behavior-determining organization, operative change, evidence bearing on an improvement objective — the definition's three base terms. All three rest on behavioral authority: consumer, channel, force.
• The definition classifies its boundary cases without ad hoc exceptions — ten cases, from gradient learning to accidental self-modification.
• Measuring autonomy well enough to see it improve is an open problem — a per-function profile locates a system but cannot yet show it becoming more autonomous.

Related Tags

• foundations — the broader core theory this sits inside
• constraining — methodological closure tracks retained settlement of consequential choices in a governed pathway
• computational-model — reflection and intercession as computational concepts generalized to socio-technical boundaries

Other tagged notes

• A benchmark that holds the client fixed exports the least-warrantable decisions by design - Why a 'matches a competent remote contractor given the same brief, tools, and feedback' comparison measures capability under a fixed client role rather than closure: the decisions it holds constant are the warrant-hard residue
• A consumption channel delivers force without the history that earned it - A consumption path can promote content into a higher-force role without checking whether an authorization covers that content, version, and use
• A failure explanation becomes search control only when it changes a later branch decision - An explanation of a failed branch becomes operative search control only when its retention changes a later choice about scope, priority, probing, continuation, or abandonment
• A method's ceiling bounds the method, not the transfer it already made - Separates envelope expansion, where a responsibility leaves the residual human work, from performance gains inside a fixed envelope, so a bounded method reaching its ceiling does not retract the transfer it already made
• A retained-theory intervention isolates one explicit theory surface, not the system's whole program theory - Varying declared retained theory while holding weights and symbolic state fixed estimates the causal contribution of that explicit theory surface, not possession of the composite's whole program theory
• A search controller is tested by what it brings to stronger evaluation - A search controller should be evaluated by the branches and probes it routes into stronger evaluation, not by treating every provisional judgment as an acceptance claim
• A theory's prototype standing is its revision cost: external binding plus lost investment - A theory's prototype standing is its expected revision cost — external binding plus the investment a revision discards — so natural-language versus symbolic form determines neither component and acceptance status is a separate axis
• An omitted improvement-loop function and a frozen one need different repairs - Five proposal-selection systems expose frozen functions, while a direct-update contrast shows why absence of a gate is not omission; HyperAgents supplies a preliminary partial unfreezing
• Backtracking keeps lightweight search control provisional - Backtracking preserves the provisional status of a heuristic branch choice by restoring an earlier usable state and redirecting search after contrary evidence
• Causal and proof obligations are two formal routes to assessing explanatory-reach - Causal and proof obligations demonstrate two ways formal symbolic systems can assess explanatory-reach inside a warranted model
• Citing retained theory at the decision point is a mediation trace - A decision record that cites the theory it followed supplies cheap, checkable evidence that the theory was consumed — necessary for a record-based mediation claim, but short of showing correct or load-bearing use
• Commonplace as a reflective self-improving system - Commonplace witnesses that a human-inclusive KB can be reflectively self-improving on one pathway despite uneven coverage and human-gated design judgment
• Disconnected witnesses do not establish a full causal path through theory - Theory use, outcome, theory revision, and later use establish theory-mediated learning only when their witnesses identify the joins of the same full causal path
• Distinct residue classes require distinct functions in a self-improving architecture - Distinct residue classes require distinct functional roles; the current natural-language, parametric, symbolic, and evidential split is one inspectable realization, not a theorem about permanent carriers
• Gödel machines are a proof-governed case of reflective self-modification - The Gödel machine realizes reflective self-modification with a proof-gated acceptance rule, gaining model-relative rigor at the cost of excluding useful changes it cannot prove
• Holding a program theory means sustaining coherent search under delayed feedback - At the least-warrantable point of open-ended program modification, Naur's coherent-modification test asks whether a fallible program-specific theory can keep search, backtracking, and revision coherent until delayed evidence arrives
• Improvements outside the admitted formal language need a pre-formal stage somewhere - An improvement whose concepts have no expression in a loop's admitted formal language is reached only through a pre-formal stage, inside the loop or fixed at design time in the choice of language; translation relocates that stage
• Lightweight search control allocates further search without licensing adoption - A search judgment is lightweight when its authority stops at allocating further investigation, probing, continuation, suspension, or abandonment rather than licensing an operative change
• Machinery persists by warrant, not position, in a reflective loop - Sutton's build-mode assumes a meta-method outside the learned system, exempt from selection by position. A reflective loop has no outside: machinery is artifacts in loop scope, the boundary moves per artifact, and persistence must be earned
• Moving the interpretation–enforcement boundary requires cross-form coverage - Moving responsibility between model-interpreted rules and formal enforcement crosses natural-language and symbolic forms, so governing the transfer requires coverage of both and their mapping
• Natural-language project state may specialize weight-resident search heuristics - The natural-language part of project state may specialize general search heuristics already represented in an LLM's weights by supplying current intent, theory, branch history, and constraints
• Open-ended improvement must allocate search before decisive evaluation is available - Open-ended improvement must choose which questions, candidates, experiments, or proof paths to develop before decisive evidence about them is available; even a Gödel machine's proof gate retains this prior search problem
• Preferential codification concentrates less predictable work at the agent boundary - Explains the negative-selection mechanism by which preferential codification changes the composition of work retained at an agent boundary
• Reach-assessment - Definition — judging whether a commitment's claimed explanatory-reach is genuine across natural-language, symbolic, and distributed-parametric forms
• Stale self-description conceals its own staleness - What artifact drift adds when it is reflexive: the process that would detect it consults the artifact that drifted, the trigger has no edit event to hook, and synchronization load scales with autonomy
• The 2026-08-30 Commonplace revision used retained theory to guide computational search - A 2026-08-30 Commonplace revision shows retained project theory guiding computational search while the operator supplied decisive global-fit selection
• Theory-mediated system learning combines runtime self-modeling with empirical theory refinement - Theory-mediated system learning joins runtime self-modeling and self-adaptation with empirical refinement of fallible explicit theories; Workspace Optimization is a contemporary implementation analogy rather than the overall closest antecedent
• Three 2026 harnesses retain rules or weights, not a revisable theory - Prime Agent, Recuris, and Apodex 1.1 on the theory-mediated, reflective, self-improving grid: the artifact loops retain rules and gated patches with no revisable theory guiding patch search; Apodex retains unaddressable weights
• Tool usefulness, computational autonomy, warrant, and system power are separate dimensions - Tool usefulness, computational autonomy, warrant, and system power move independently in a human-agent system, so a progress claim has to say which one moved and autonomy gains do not license power claims
• Warranted transfer out of the human cut leaves people the hardest-to-warrant decisions - When a system preferentially transfers decisions whose premises, criteria, and checks are available, the remaining human decisions become harder to warrant per decision; this predicts a residue composition, not structural computational openness
• Weakly discriminated qualities tend to be underselected - Statistical conjecture: under named proposal-selection conditions, unequal oracle discrimination yields unequal enrichment; absolute degradation needs an additional directional mechanism
• World models assess explanatory-reach through action-conditioned prediction - Learned world models can assess explanatory-reach when action-conditioned predictions are tested across the interventions or shifts a commitment claims