deploy-time-learning

Type: kb/types/tag-readme.md

The organizing framework of the learning-theory area: deployed systems adapt through symbolic artifacts — durable, inspectable, verifiable — filling the gap between training and in-context learning. Notes here cover the framework itself, the learning fundamentals it rests on, and the feedback signals that govern its quality. A child of learning-theory.

The framework

• deploy-time learning is the missing middle — three timescales of system adaptation; co-evolving natural-language and code as agile-style deploy-time learning
• the verifiability gradient — the ladder deploy-time artifacts sit on, from restructured prompts through schemas and evals to deterministic code
• readable-artifact loop is the tractable unit for continual learning — the loop that makes behaviour change cheap: readable system-definition artifacts revised in place
• treat continual learning as representational-form coevolution — the system and its knowledge substrate evolve together rather than one training the other

Learning fundamentals

• learning is not only about generality — accumulation as the basic operation, with explanatory-reach as its key property; capacity decomposes into generality vs a reliability/speed/cost compound
• LLM learning phases fall between human learning modes — warns against literal human-LLM learning analogies
• in-context learning presupposes context engineering — "no continual learning needed" relocates the learning to the system layer rather than eliminating it
• choosing what to learn requires both validity and learning-value gates — accumulation policy: true is necessary but not sufficient
• abstract an experience only when you can state where the lesson stops — the abstract-vs-preserve decision: generalize only when the lesson's boundary is statable, else keep the instance
• use tests a decomposition locally; retained rationale makes transfer testable — the design-act case of the same boundary problem: the reasoning leaves no residue in the product, so it is retained at design time or it is gone

Feedback and signal quality

• changing requirements conflate genuine change with disambiguation failure — short iterations bound interpretation-error propagation, not just change-response latency
• evaluation automation is phase-gated by comprehension — comprehension and specification must precede optimization, or automation amplifies the wrong objective
• diagnostic richness constrains outer-loop learning quality — what the learning loop can learn is bounded by what its diagnostics distinguish
• apparent success is an unreliable health signal — completion without verification teaches the wrong lesson

Related Tags

• constraining — the primary hardening mechanism inside the framework
• discovery — the operation that produces the framework's highest-explanatory-reach artifacts

Other tagged notes

• A compact, refreshable whole-picture narrative can replace infeasible fragment reconciliation - Holistic rewrite shifts reconciliation from each consumer to the author, but only when the whole-picture narrative can fit within effective context and be refreshed before the narrative goes stale
• Agent context is constrained by soft degradation, not hard token limits - Agent context is bounded by silent reliability degradation across volume, complexity, and relevance/interference, not just by provider token limits
• 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
• Continual learning's open problem is governing behaviour change, not storing knowledge - Storing content is infrastructure; continual learning's open problem is choosing, validating, and coordinating fast, reach-bearing behaviour-changing writes across three forms — parametric weights, natural-language theories, and symbolic artifacts
• Learning inside a fixed decomposition inherits its mistakes - Why optimization cannot repair consequential distinctions, responses, or mappings outside the effective update space of a fixed task decomposition
• Links encode conditional possibilities, not obligations - Links encode conditional possibilities, not obligations — every label must name a specific reader-need (the condition under which following pays off); content required for all reachable readers should be inlined, not linked
• Localized retention pays when sparse changes have bounded impact in a matching decomposition - Addressable retention localizes a sparse change when units match its decomposition; total adaptation stays local only when the affected units also have a small, explicit impact closure
• 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
• Oracle accumulation improves selection for later candidates in its maintained domain - A failure retained as a lesson helps tasks that retrieve it; retained as a maintained check it improves selection for later candidates in its domain and amortizes validation
• Psychology-to-agent transfer needs per-principle failure-mode testing - Brainstorming a methodology for evaluating cognitive-science-to-agent transfer — assembled from three existing KB notes and tested against Youssef's five psychology principles as worked examples
• Scaling absorbs scaffolding at fixed task difficulty, not at the deployment frontier - Stronger models shrink the scaffolding a fixed task needs; durable deployment-specific structure recurs at the frontier only while assigned difficulty keeps pace with capability and some reliability function stays advantageous to externalize
• Soft-bound traditions as sources for context engineering strategies - Survey of twelve soft-bound traditions as candidate sources for context engineering strategies, with a three-tier assessment of what transfers, what's plausible, and what's blocked
• The bitter lesson selects production methods, not representational forms - The lesson's axis is production method — hand-crafted versus search-and-learning — not representational form. Learned localized forms are therefore a coherent scaling hypothesis, with cross-artifact credit assignment as the decisive open problem
• The bitter-lesson defense portfolio has one load-bearing member for the form-only rebuttal - The KB's bitter-lesson claims play different roles: one narrow answer to a form-only objection, an empirical burden, methodology, instrumentation, separate-objection answers, and conditional forecasts
• The deployed system, not the model alone, is the unit of learning - Because prompts, retrieval, tools, and runtime policy jointly determine deployed behavior, model-only learning leaves consequential system choices fixed
• The Meta-Harness ablation does not identify episode-backed theory formation - Why the summaries-hurt ablation does not identify the effect of scoped theory formation alongside retained episodes, while still supplying adverse evidence about condensed feedback