Items Directory

Type: kb/types/index.md

← Parent

• Addressability in self-improving systems (note) - Self-improvement can compound without reflection — parametric learners do — but non-reflective retention gives only indirect handles; reflective retention makes the changed object addressable
• Agent statelessness makes deterministic routing architectural, not learned (note) - Agents never develop navigation intuition — every session is day one — so all knowledge routing infrastructure (skills, type templates, routing tables, naming conventions, activation triggers) is permanent architecture, not scaffolding that learners outgrow
• Agent statelessness makes routing architectural, not learned (note) - Agents never develop navigation intuition — every session is day one — so all knowledge routing infrastructure (skills, type templates, routing tables, naming conventions, activation triggers) is permanent architecture, not scaffolding that learners outgrow
• Agent statelessness makes routing architectural, not learned (note) - Agents never develop navigation intuition — every session is day one — so all knowledge routing infrastructure (skills, type templates, routing tables, naming conventions, activation triggers) is permanent architecture, not scaffolding that learners outgrow
• Agent statelessness makes routing architectural, not learned (note) - Agents never develop navigation intuition — every session is day one — so all knowledge routing infrastructure (skills, type templates, routing tables, naming conventions, activation triggers) is permanent architecture, not scaffolding that learners outgrow
• Agent statelessness makes typed routing architectural, not learned (note) - Agents never develop navigation intuition — every session is day one — so all knowledge routing infrastructure (skills, type templates, routing tables, naming conventions, activation triggers) is permanent architecture, not scaffolding that learners outgrow
• Error messages that teach are a constraining technique (note) - In agent systems the error channel is an instruction channel — making errors teach the fix is nearly free and eliminates the agent's need to diagnose, an orthogonal axis to enforcement strength
• Error messages that teach are a constraining technique (note) - In agent systems the error channel is an instruction channel — making errors teach the fix is nearly free and eliminates the agent's need to diagnose, an orthogonal axis to enforcement strength
• Error messages that teach are a constraining technique (note) - In agent systems the error channel is an instruction channel — making errors teach the fix is nearly free and eliminates the agent's need to diagnose, an orthogonal axis to enforcement strength
• Error messages that teach are a constraining technique (note) - In agent systems the error channel is an instruction channel — making errors teach the fix is nearly free, an orthogonal axis to enforcement strength
• Error messages that teach are a constraining technique (note) - In agent systems the error channel is an instruction channel — making errors teach the fix is nearly free, an orthogonal axis to enforcement strength
• First-principles reasoning selects for explanatory reach over adaptive fit (note) - Adapts Deutsch's adaptive-vs-explanatory distinction to KB design — first-principles reasoning selects explanations with reach, accountable to observed fit and rival-practice tests
• Index staleness (note) - An agent trusts an index as exhaustive — a missing entry doesn't trigger search, it makes the note invisible
• Instruction specificity should match loading frequency (note) - The loading hierarchy (CLAUDE.md → skill descriptions → skill bodies → task docs) should match instruction specificity to loading frequency — always-loaded context competes for attention every session
• Instruction specificity should match loading frequency (note) - The loading hierarchy (CLAUDE.md → skill descriptions → skill bodies → task docs) should match instruction specificity to loading frequency — always-loaded context competes for attention every session
• Instruction specificity should match loading frequency (note) - The loading hierarchy (CLAUDE.md → skill descriptions → skill bodies → task docs) should match instruction specificity to loading frequency — always-loaded context competes for attention every session
• Instruction specificity should match loading frequency (note) - The loading hierarchy (CLAUDE.md → skill descriptions → skill bodies → task docs) should match instruction specificity to loading frequency — the pattern production harnesses converge on
• Instruction specificity should match loading frequency (note) - The loading hierarchy (CLAUDE.md → skill descriptions → skill bodies → task docs) should match instruction specificity to loading frequency
• KB index maintenance (note) - An agent trusts an index as exhaustive — a missing entry doesn't trigger search, it makes the note invisible
• Reflection and addressability (note) - Self-improvement can compound without reflection — parametric learners do — but non-reflective retention gives only indirect handles; reflective retention makes the changed object addressable
• Reflection buys addressability (note) - Self-improvement can compound without reflection — parametric learners do — but non-reflective retention gives only indirect handles; reflective retention makes the changed object addressable
• Reflection buys addressability (note) - Self-improvement can compound without reflection — parametric learners do — but non-reflective retention gives only indirect handles; reflective retention makes the changed object addressable
• Spec mining is codification's operational mechanism (note) - Operationalizes codification by extracting deterministic verifiers from observed stochastic behavior — the mechanism that converts blurry-zone components into calculators
• Spec mining is codification's operational mechanism (note) - Operationalizes codification by extracting deterministic verifiers from observed stochastic behavior — the mechanism that converts blurry-zone components into calculators
• Spec mining is codification's operational mechanism (note) - Operationalizes codification by extracting deterministic verifiers from observed stochastic behavior — the mechanism that converts blurry-zone components into calculators
• Spec mining is codification's operational mechanism (note) - Operationalizes codification by extracting deterministic verifiers from observed stochastic behavior — the mechanism that converts blurry-zone components into calculators
• Spec mining is codification's operational mechanism (note) - Operationalizes codification by extracting deterministic verifiers from observed stochastic behavior — the mechanism that converts blurry-zone components into calculators
• Stale indexes are worse than no indexes (note) - An agent trusts an index as exhaustive — a missing entry doesn't trigger search, it makes the note invisible
• Stale indexes are worse than no indexes (note) - An agent trusts an index as exhaustive — a missing entry doesn't trigger search, it makes the note invisible
• Stale indexes are worse than no indexes (note) - An agent trusts an index as exhaustive — a missing entry doesn't trigger search, it makes the note invisible
• Stale indexes are worse than no indexes (note) - An agent trusts an index as exhaustive — a missing entry doesn't trigger search, it makes the note invisible
• Stale indexes are worse than no indexes (note) - An agent trusts an index as exhaustive — a missing entry doesn't trigger search, it makes the note invisible
• Stale indexes are worse than no indexes (note) - An agent trusts an index as exhaustive — a missing entry doesn't trigger search, it makes the note invisible
• Storing LLM outputs is constraining (note) - Keeping a specific LLM output resolves semantic underspecification and freezes one run against execution indeterminism - a constraining move applied to artifacts
• Storing LLM outputs is constraining (note) - Keeping a specific LLM output resolves semantic underspecification and freezes one run against execution indeterminism - a constraining move applied to artifacts
• Storing LLM outputs is constraining (note) - Keeping a specific LLM output resolves semantic underspecification and freezes one run against execution indeterminism - a constraining move applied to artifacts
• Storing LLM outputs is constraining (note) - Keeping a specific LLM output resolves semantic underspecification and freezes one run against execution indeterminism - a constraining move applied to artifacts
• Storing LLM outputs is constraining (note) - Keeping a specific LLM output resolves semantic underspecification and freezes one run against execution indeterminism - a constraining move applied to artifacts
• Storing LLM outputs is constraining (note) - Keeping a specific LLM output resolves semantic underspecification and freezes one run against execution indeterminism - a constraining move applied to artifacts
• Storing LLM outputs is constraining (note) - Keeping a specific LLM output resolves semantic underspecification and freezes one run against execution indeterminism - a constraining move applied to artifacts
• The boundary of automation is the boundary of deterministic verification (note) - Synthesis — oracle theory, labor economics, frontier-lab capability predictions, and supply-chain integrity evidence converge on verification cost as the primary structural determinant of automation
• The boundary of automation is the boundary of symbolic verification (note) - Synthesis — oracle theory, labor economics, frontier-lab capability predictions, and supply-chain integrity evidence converge on verification cost as the primary structural determinant of automation
• The boundary of automation is the boundary of verification (note) - Synthesis — oracle theory, labor economics, frontier-lab capability predictions, and supply-chain integrity evidence converge on verification cost as the primary structural determinant of automation
• The boundary of automation is the boundary of verification (note) - Synthesis — oracle theory, labor economics, frontier-lab capability predictions, and supply-chain integrity evidence converge on verification cost as the primary structural determinant of automation
• The boundary of automation is the boundary of verification (note) - Synthesis — oracle theory, labor economics, frontier-lab capability predictions, and supply-chain integrity evidence converge on verification cost as the primary structural determinant of automation
• The boundary of automation is the boundary of verification (note) - Synthesis — oracle theory, labor economics, frontier-lab capability predictions, and supply-chain integrity evidence converge on verification cost as the primary structural determinant of automation
• Warranted autonomy is bounded by oracle domain (note) - Bare autonomy is free, but warranted evaluation autonomy extends only to the candidates an oracle can assess with the required confidence
• Warranted autonomy is bounded by oracle domain (note) - Bare autonomy is free, but warranted evaluation autonomy extends only to the candidates an oracle can assess with the required confidence