constraining

Type: types/tag-readme.md

Constraining narrows the space of valid interpretations an artifact admits, from conventions to deterministic code; relaxing deliberately widens that space again. Assign this tag when an artifact explains, applies, tests, or decides when to use or reverse that narrowing. Merely choosing an output or improving task accuracy is insufficient unless the interpretation space is at issue. LLM reliability covers output deviations and their correction more broadly; constraining is one possible response. A child of learning-theory.

Definition and spectrum

• constraining — definition and spectrum: definitions, conventions, structured sections, schemas, validators, and deterministic code
• codification — the far end, where the medium itself changes from natural language to a symbolic artifact with formal semantics
• agentic systems interpret underspecified instructions — the foundation: the spec-to-program projection model, semantic boundaries, and the constrain/relax cycle

Instances and techniques

• Selecting an LLM output fixes a result, not its interpretation — boundary case: selection fixes result identity; it counts as constraining only when adoption also narrows which interpretations remain operative
• constraining during deployment is continuous learning — versioned constraining beats weight updates on inspectability and rollback
• spec mining as codification — observe behavior, extract deterministic rules, grow the calculator surface monotonically
• error messages that teach are a constraining technique — in agent systems the error channel is an instruction channel
• methodology enforcement is constraining — review gates and validation as constraining applied to the KB's own methodology

Deciding and reversing

• codify-versus-LLM decision heuristics — four lenses on the codify-vs-LLM decision, with evidence they come apart at the edges
• specification strategy should follow where understanding lives — when to commit: before execution, during execution, or after repeated observation
• progressive constraining commits only after patterns stabilize — the default discipline: codify after the pattern proves the need
• unified calling conventions enable bidirectional refactoring — how to commit reversibly: neural and symbolic components behind the same callable interface
• codification and relaxing navigate the bitter lesson boundary — why reversibility matters: codification is a bet that may need relaxing
• operational signals that a component is a relaxing candidate — five testable signals for detecting when to reverse codification

Related Tags

• deploy-time-learning — the post-release change constraining absorbs; the verifiability gradient locates constrained artifacts

Other tagged notes

• A methodology governs its own extension only as far as it settles the meta-decisions it raises - A retained methodology governs the consequential extension decisions it supplies or imports; actor competence can carry the process further without making those choices settled by the method
• 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
• Ad hoc prompts extend the system without schema changes - Any system with an LLM agent layer can absorb new requirements through natural language prompts without changing the deterministic base
• Bidirectional codification as a comparative test - Proposal: promote bidirectional codification from design guidance to a comparative conjecture, tested by evolving the same task stream under natural-language-only, symbolic-only, one-way promotion, and bidirectional codify-and-relax regimes
• Code complements the weight–prompt pair with independently executed symbolic operations - A model-mediated operation is instantiated by weights plus prompt; code complements that pair by defining operations whose consequences a symbolic runtime executes without reinterpreting the prompt
• Commitment, not derivation, creates new ground truth - Derivation — claims recoverable from the source, nothing added — leaves the source as ground truth; what adds unentailed resolutions becomes ground truth at commit, repaired by supersession
• Constraining and extraction can trade generality for reliability, speed, or cost - Constraining narrows interpretation and extraction produces focused use-shaped artifacts; both can trade generality for reliability, speed, or cost when task fit is good
• Enforcement without structured recovery is incomplete - The enforcement gradient covers detection and blocking but has no recovery column — recovery strategies (corrective → fallback → escalation) are the missing layer, and oracle strength determines which are viable at each level
• Exact implementation does not validate a requirement against its objective - An artifact can exactly implement a requirement while the requirement remains a conjectured proxy for a declared objective; assess each named path separately, and attribute failure to the link without erasing local correctness
• 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
• Inspectable artifact, not supervision, defeats the blackbox problem - Chollet frames agentic coding as ML producing blackbox codebases — codification counters this not by requiring human review but by choosing readable artifacts (code, prompts, schemas) that any agent can inspect, diff, test, and verify
• Legal drafting solves the same problem as context engineering - Legal drafting parallels context engineering because both write ambiguous natural-language specifications for judgment-based interpreters, but law develops constraining more than codification
• LLM-executed methodologies are metacircular interpreters, not compilers - Self-hosting LLM methodologies are closer to metacircular interpreters than compilers: agents re-interpret natural-language rules each session, while stable paths codify into validators and commands
• LLM↔code boundaries are natural checkpoints - LLM↔code boundaries expose concrete inputs and outputs for inspection and replay; deterministic execution preserves rather than corrects a wrongly interpreted argument
• Methodology with incomplete coverage and its live theory fallback form a two-layer execution system - In open or incompletely covered domains, the theory-derived fast path and live theory fallback co-execute while methodology-native content follows a separate maintenance regime
• 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
• Opacity is a scale threshold, not a class property - Opacity is not a representational form; any representation becomes practically opaque at sufficient scale, though distributed-parametric artifacts cross that threshold earliest.
• Reflective coverage is graded across representational forms - Reflective coverage is stated per represented form and operation profile; control of an external dependency does not make that dependency part of the system's reflective coverage
• The bitter lesson selects against unearned reach, not against structure - The lesson selects against claims whose reach was asserted rather than earned by a refuting test, not against structure or origin — theory search in readable forms is its own method; earned reach protects the claim, not its carrier
• The verifiability gradient - Symbolic artifacts sit on a gradient from loose natural-language to deterministic code; higher-verifiability artifacts support tighter iteration loops, and learning moves artifacts along it in both directions
• Underspecification and indeterminism complicate programming for prompts in distinct ways - Indeterminism doubles test runs (statistical testing over distributions); underspecification doubles test targets (spec analysis for ambiguity). Conflating the two leads to misdiagnosis