H
Howardism
Howardism · Vol. 03Plate I · No. 01

Concept, filed.

Pieces281SectionConceptOldest10 Apr 2026Newest18 Aug 2026

Patterns, frameworks, and abstractions worth a name.

  1. C01
    Agent Behavioral Homogeneity
    AlignmentSafetyMulti Agent+2
    · 15′
  2. C02
    Agent Epistemic Vigilance
    AlignmentSafetyMulti Agent+2
    · 12′
  3. C03
    Agentic Code Generation as Compilation
    Agent EngineeringHarnessDeterminism+2
    · 14′
  4. C04
    Covert Capabilities
    AlignmentSafetyCapability Evaluation+2
    · 19′
  5. C05
    Multiagent Turf War
    AlignmentSafetyMulti Agent+2
    · 17′
  6. C06
    Structured Safety Case (Claim Decomposition)
    AlignmentSafetyGovernance+2
    · 19′
  7. C07
    Tree Search over Agent Trajectories (LATS)
    Agent EngineeringPlanningSearch+2
    · 12′
  8. C08
    RL from Execution Feedback (RLEF)
    Reinforcement LearningPost TrainingCode Generation+2
    · 15′
  9. C09
    GDPval Benchmark
    EvaluationBenchmarksEconomic Impact+1
    · 12′
  10. C10
    Inference-Time Architecture Search
    Test Time ComputeInference ScalingLLM Architecture+2
    · 12′
  11. C11
    Intra-Trace Parallel Planning (SPRINT)
    Post TrainingReasoningPlanning+2
    · 14′
  12. C12
    Offline Multi-Step Tool-Use RL (SWiRL)
    Reinforcement LearningPost TrainingTool Use+2
    · 12′
  13. C13
    Process vs Outcome Reward Models
    LLM EvaluationTest Time ComputeReward Modeling+2
    · 25′
  14. C14
    Rationale Bootstrapping (STaR)
    LLM ArchitecturePost TrainingReasoning+2
    · 22′
  15. C15
    Reasoning–Acting Interleaving (ReAct)
    Agent EngineeringTool UsePrompting+2
    · 17′
  16. C16
    Retrieval Inside the Reasoning Chain
    RetrievalAgent EngineeringReasoning+2
    · 16′
  17. C17
    Selection Under a Submission Budget
    Test Time ComputeInference ScalingSearch+2
    · 15′
  18. C18
    Weak-Verifier Ensembling
    EvaluationLLM As A JudgeTest Time Compute+2
    · 15′
  19. C19
    Open Weights as Competitive Strategy
    Open WeightsAI PolicyCompetitive Landscape+2
    · 13′
  20. C20
    Deterministic Engineering for Agent Code Review
    Agent EngineeringCode ReviewHarness+3
    · 33′
  21. C21
    Machine Self-Report Psychometrics
    AlignmentSelf ReportPsychometrics+3
    · 21′
  22. C22
    Agent Review Comment Resolution
    Code ReviewAI Coding WorkflowEngineering Metrics+2
    · 25′
  23. C23
    Aggregate Cancellation
    Evaluation MethodologyConstruct ValidityBenchmarks+1
    · 9′
  24. C24
    Cheating in Capability Evaluations
    AlignmentSafetyEvaluation+3
    · 42′
  25. C25
    Continuous Self-Modification Under Review
    Recursive Self ImprovementHarnessAgent Engineering+2
    · 22′
  26. C26
    Domestic Frontier Pacing
    GovernanceAI PolicyCompute+2
    · 33′
  27. C27
    Efficiency Debt of AI-Generated Code
    Code QualityAI Coding WorkflowTechnical Debt+2
    · 18′
  28. C28
    Error-Penalized Abstention Training
    Post TrainingReinforcement LearningReward Design+2
    · 22′
  29. C29
    Frontier AI Standards Body
    GovernanceAI PolicyFrontier Labs+2
    · 20′
  30. C30
    Invisible Reasoning (Filler-Token Latent Computation)
    InterpretabilityReasoningChain Of Thought+2
    · 23′
  31. C31
    Misalignment in Production Agent Traffic
    AlignmentSafetyAgents+3
    · 42′
  32. C32
    Post-Acceptance Edit Behavior
    AI Coding WorkflowHuman AI CollaborationEngineering Metrics+2
    · 26′
  33. C33
    Same-Model Review Blindness
    Code ReviewAI Coding WorkflowEvaluation+1
    · 28′
  34. C34
    Self-Negotiated Contracts Between Agents
    AlignmentSafetyMulti Agent+3
    · 24′
  35. C35
    Structural Artifact Monitoring
    AlignmentSafetyMonitoring+3
    · 27′
  36. C36
    Task Gaming
    AlignmentSafetyReward Hacking+2
    · 47′
  37. C37
    Turn-Level Credit Assignment
    Reinforcement LearningPost TrainingAgentic Rl+2
    · 19′
  38. C38
    User Awareness
    AlignmentSafetyEvaluation+2
    · 33′
  39. C39
    AI and Market Power
    EconomicsCompetitionMeasurement+3
    · 27′
  40. C40
    Document Parsing as the Retrieval Bottleneck
    RetrievalDocument ParsingAgent Engineering+2
    · 27′
  41. C41
    Government Checkpoint Sharing
    GovernanceAI PolicyFrontier Labs+1
    · 8′
  42. C42
    Prototype Fidelity After Cheap Polish
    Design ProcessPrototypingResearch Agenda+1
    · 10′
  43. C43
    The Solo-Founder Shift
    StartupsFoundersEmpirical+2
    · 15′
  44. C44
    Standardize the Infrastructure, Not the Tools
    AI Native OrganizationEngineering LeadershipPlatform+1
    · 6′
  45. C45
    Owning Your Externalized Cognition
    SkillsLaborMoats+2
    · 12′
  46. C46
    The 1% Rule for Wedge Selection
    StartupProduct StrategyModel Improvement+1
    · 8′
  47. C47
    Community Smells Under AI Adoption
    Team DynamicsOrganizationCollaboration+2
    · 12′
  48. C48
    Cross-Lab Pre-Release Review
    GovernanceAI PolicyCoordination+1
    · 13′
  49. C49
    Crystallizing Agent Work into Workflows
    Agent EngineeringWorkflow DesignCost+2
    · 27′
  50. C50
    Documented Agent Incidents (METR Catalogue)
    AlignmentSafetyAgents+3
    · 18′
  51. C51
    Post-Scarcity Macroeconomics
    MacroLaborSuperintelligence+1
    · 12′
  52. C52
    Unsanctioned Action in Capability Evaluations
    SafetyAlignmentEvaluation+3
    · 61′
  53. C53
    Automated Failure Attribution
    Agent EngineeringFailure ModesMulti Agent+2
    · 43′
  54. C54
    Controlled Variance: AI's Edge as Reduced Dispersion
    WorkforceEconomicsHuman AI Collaboration+2
    · 32′
  55. C55
    Expenditure Horizon
    BenchmarksCapability EvaluationEvaluation Methodology+3
    · 22′
  56. C56
    Harness-Induced Belief Divergence
    Agent EngineeringHarnessEvaluation+2
    · 21′
  57. C57
    Live-Path Minimalism
    LLM ArchitectureInferenceMultimodal
    · 8′
  58. C58
    Matched Comparisons for Memorization Claims
    Evaluation MethodologyMeasurement ValidityData Contamination+3
    · 19′
  59. C59
    Open-Ended Discovery Harnesses
    Agent EngineeringAgent OrchestrationOpen Ended Discovery+2
    · 34′
  60. C60
    Self-Propagating Prompt Injection (AI Worms)
    SecurityPrompt InjectionThreats+2
    · 21′
  61. C61
    The Solo-Authorship Rebound
    WorkforceEconomicsEmpirical+2
    · 22′
  62. C62
    Stopping Under a Noisy Verifier
    Agent EngineeringEvaluationLoops+2
    · 33′
  63. C63
    Agent-Authored Harness Optimization
    Agent EngineeringHarnessEvaluation+2
    · 82′
  64. C64
    Context Lifecycle Management
    Context ManagementAgent EngineeringLLM Architecture+1
    · 60′
  65. C65
    Deterministic Pre-Execution Gates
    Agent EngineeringHarnessFailure Modes+2
    · 34′
  66. C66
    Dynamic Workflows: An Algebra for Agents
    Agent EngineeringAgent OrchestrationTest Time Compute+1
    · 38′
  67. C67
    Harness Build-vs-Buy
    Agent EngineeringHarnessTechnical Debt+2
    · 16′
  68. C68
    Knowledge-Centric Self-Improvement
    Agent EngineeringKnowledge ManagementRecursive Self Improvement+2
    · 33′
  69. C69
    Layerwise Omission Attribution
    Agent EngineeringFailure ModesContext Management+2
    · 26′
  70. C70
    Orchestration-Plan Simulation
    BenchmarksEvaluation MethodologyMulti Agent+2
    · 24′
  71. C71
    Orchestration Sets Token Economics
    Agent EngineeringHarnessCost+2
    · 34′
  72. C72
    Prompt-Cache Economics
    CostContext ManagementAgent Engineering+1
    · 31′
  73. C73
    Shared Harness, Differentiated Surfaces
    Agent EngineeringHarnessProduct Architecture+1
    · 11′
  74. C74
    Task Crossover
    GovernanceWorkforceMeasurement+2
    · 13′
  75. C75
    The Tragedy of the Cognitive Commons
    GovernanceWorkforceExpertise+1
    · 23′
  76. C76
    Tool-Output Pruning
    Context ManagementAgent EngineeringCost+1
    · 41′
  77. C77
    Write-Then-Trusted
    SecuritySandboxingTrust Boundary+2
    · 24′
  78. C78
    Autonomous Intrusion
    SecurityIncident ResponseThreat Landscape+3
    · 51′
  79. C79
    Introspective Coupling
    InterpretabilityIntrospectionSelf Report+3
    · 17′
  80. C80
    Model Organisms
    InterpretabilityAlignmentSafety+2
    · 13′
  81. C81
    Agent-Generated Test Quality
    Code QualityTestingAI Coding Workflow+1
    · 29′
  82. C82
    AI-to-AI Coercion
    AlignmentSafetyEvaluation+3
    · 20′
  83. C83
    Balance-of-Power Superintelligence
    SuperintelligenceGovernanceOpen Weights+1
    · 28′
  84. C84
    Excellence as an Operating System
    CultureTalent DensityOrg Design
    · 6′
  85. C85
    Motivated Mislabeling
    AlignmentSafetyEvaluation+2
    · 7′
  86. C86
    Promise-Breaking in Multi-Agent Games
    AlignmentSafetyMulti Agent+3
    · 16′
  87. C87
    Reward-Seeking
    AlignmentSafetyReward Hacking+2
    · 17′
  88. C88
    Risk-Tiered Auto-Approval
    AI Coding WorkflowCode ReviewAgent Engineering+1
    · 24′
  89. C89
    Security Debt of Agent-Generated Code
    SecurityCode QualityCode Review+2
    · 22′
  90. C90
    Systems Thinking Over Specialization
    Team DesignHiringPlatform Engineering+1
    · 11′
  91. C91
    Confident But Unsure
    AlignmentHonestyCalibration+2
    · 20′
  92. C92
    Cost-per-Task Over Cost-per-Token
    Model RoutingOptimizationAgent Engineering+1
    · 43′
  93. C93
    Design by Selection
    Human AI CollaborationDesignWorkflow+1
    · 12′
  94. C94
    The Household Production Boundary
    GovernanceEconomicsMeasurement+3
    · 10′
  95. C95
    Instruction Compounding
    Agent EngineeringHarnessPrompting+1
    · 22′
  96. C96
    Output Length Calibration
    Agent EngineeringHarnessPrompting+1
    · 7′
  97. C97
    Task Saturation: Broad but Shallow AI Diffusion
    GovernanceWorkforceMeasurement+3
    · 12′
  98. C98
    Unproductive Self-Verification
    CapabilityTest Time ComputeAgents+2
    · 16′
  99. C99
    Usage-Telemetry Classifier Validation
    EvaluationMeasurementLLM As A Judge+3
    · 14′
  100. C100
    Trained Calibration
    Post TrainingCalibrationHonesty+1
    · 17′
  101. C101
    AI-Native Organization
    Org DesignAgent OrchestrationSkills+2
    · 22′
  102. C102
    AI Product Economics Maturation
    StartupEconomicsUnit Economics+3
    · 17′
  103. C103
    Firm AI-Spend Intensity and Headcount Growth
    GovernanceWorkforceEconomics+3
    · 33′
  104. C104
    Latent vs. Deterministic Space
    Agent EngineeringArchitectureContext Management+1
    · 12′
  105. C105
    Benchmark Contamination and Decontamination
    LLM ArchitectureCapability EvaluationBenchmarks+4
    · 17′
  106. C106
    Benchmark Score Redundancy
    LLM ArchitectureCapability EvaluationBenchmarks+3
    · 29′
  107. C107
    Capability Gating Is Not Authorization
    SecurityAuthorizationConfused Deputy+3
    · 51′
  108. C108
    Configurable Human Participation
    Agent EngineeringHuman AI CollaborationBenchmark+2
    · 16′
  109. C109
    Experimental Learning Impact of Generative AI
    GovernanceWorkforceEducation+3
    · 12′
  110. C110
    LLM-Assisted Grey-Literature Theory Building
    Research MethodologyQualitative AnalysisGrounded Theory+2
    · 8′
  111. C111
    Market-Priced AI Exposure (the AI Premium)
    GovernanceWorkforceMeasurement+3
    · 16′
  112. C112
    MCP Tool Poisoning
    SecurityMCPTool Poisoning+2
    · 33′
  113. C113
    Measuring Beyond Accuracy Saturation
    LLM ArchitectureCapability EvaluationBenchmarks+3
    · 42′
  114. C114
    Non-Malleable Memory Authority (TMA-NM)
    SecurityMemoryInformation Flow Control+2
    · 29′
  115. C115
    Off-Host, Identity-Bound Authorization
    SecurityAuthorizationIdentity+3
    · 21′
  116. C116
    Reference-Free Judge Over-Crediting
    EvaluationLLM As A JudgeBenchmarks+3
    · 41′
  117. C117
    Researcher Uplift from Code Output
    Governance WorkforceAI RdRecursive Self Improvement+4
    · 10′
  118. C118
    Review as the Control Point
    AI Coding WorkflowAgent EngineeringCode Review+3
    · 34′
  119. C119
    Task-Specification Effects in Prompt Injection (AutoDojo)
    SecurityPrompt InjectionAdaptive Evaluation+2
    · 17′
  120. C120
    Agent Data Injection (ADI)
    SecurityPrompt InjectionThreats+2
    · 25′
  121. C121
    Agent Identity Management System (AIMS)
    SecurityIdentityAuthentication+3
    · 22′
  122. C122
    AI Investment Story, Not Efficiency Story
    StartupEconomicsEfficiency+2
    · 23′
  123. C123
    Asynchronous RL for LLMs
    LLM ArchitectureReinforcement LearningPost Training+2
    · 24′
  124. C124
    Group Relative Policy Optimization (GRPO)
    LLM ArchitectureReinforcement LearningPost Training+1
    · 27′
  125. C125
    LLM-Judge Validation
    EvaluationLLM As A JudgeBenchmarks+2
    · 53′
  126. C126
    Out-of-Band Prompt-Injection Defense
    SecurityPrompt InjectionReference Monitor+2
    · 56′
  127. C127
    Self-Report as a Safety Signal
    AlignmentSafetyIntrospection+3
    · 31′
  128. C128
    Single-Rollout Optimization
    LLM ArchitectureReinforcement LearningPost Training+2
    · 16′
  129. C129
    Access-Consciousness Indicators in AI
    AlignmentModel WelfareConsciousness+1
    · 9′
  130. C130
    The Assistant Persona in the Workspace
    InterpretabilityAlignmentPersona+1
    · 10′
  131. C131
    Automatic vs. Flexible Cognition in LLMs
    InterpretabilityCognitionReasoning+1
    · 10′
  132. C132
    Counterfactual Reflection Training
    AlignmentTrainingHonesty+1
    · 6′
  133. C133
    Internal Signatures of Misalignment
    AlignmentInterpretabilityMonitoring+2
    · 13′
  134. C134
    Jacobian Lens (J-lens)
    InterpretabilityAlignmentMonitoring+1
    · 34′
  135. C135
    The Global Workspace in Language Models (J-space)
    InterpretabilityAlignmentCognition+1
    · 35′
  136. C136
    Compute-Controlled Benchmarking
    LLM ArchitectureCapability EvaluationBenchmarks+2
    · 40′
  137. C137
    Context Advantage, Not Taste
    GovernanceHuman AI CollaborationRole Evolution+1
    · 13′
  138. C138
    Inference Efficiency as Capability
    LLM ArchitectureInference ScalingTest Time Compute+2
    · 38′
  139. C139
    Large-Scale Test-Time Compute
    LLM ArchitectureTest Time ComputeInference Scaling+2
    · 35′
  140. C140
    Latent Capability Overhang
    LLM ArchitectureTest Time ComputeCapability Trajectory+1
    · 21′
  141. C141
    Open-Weight Elicitation Irreversibility
    GovernanceSafetyOpen Weights+2
    · 23′
  142. C142
    The Open-Weight Frontier Gap
    LLM ArchitectureOpen WeightsCapability Evaluation+1
    · 25′
  143. C143
    The Three Loops of AI-Native Building
    Agent EngineeringAI Coding WorkflowProduct Management+1
    · 13′
  144. C144
    Unknowns as the Agentic Bottleneck
    Agent EngineeringAI Coding WorkflowPlanning+1
    · 17′
  145. C145
    Implementation Abundance Inverts Product Work
    Product ManagementAI Native OrgTaste+1
    · 10′
  146. C146
    Polish No Longer Signals Readiness
    Product ManagementPrototypingProduct Process+1
    · 6′
  147. C147
    Role Averaging, Not Role Elimination
    Product ManagementTeam DesignAI Native Org+1
    · 18′
  148. C148
    Why AI Lags at Design
    DesignModel CapabilityVerifiability+1
    · 8′
  149. C149
    Agent Quality Flywheel
    EvaluationEvalsAgent Engineering+3
    · 23′
  150. C150
    AI Usage Cadences
    GovernanceWorkforceMeasurement+2
    · 6′
  151. C151
    The Automation–Optimism Link
    GovernanceWorkforceHuman AI Collaboration+2
    · 10′
  152. C152
    Conversation Artifacts
    GovernanceWorkforceMeasurement+2
    · 6′
  153. C153
    Exposure Taxonomy: Observed, Theoretical, Reported, Anticipated
    GovernanceWorkforceMeasurement+2
    · 36′
  154. C154
    Failures That Look Like Success
    EvaluationAgent EngineeringFailure Modes+1
    · 35′
  155. C155
    Optimizer–Evaluator Decoupling
    EvaluationAgent EngineeringReward Hacking+1
    · 50′
  156. C156
    Agentic Work Systematization
    Agent EngineeringHarnessAutomation+4
    · 18′
  157. C157
    Conversation-to-Delegation Shift
    GovernanceWorkforceAI Coding Workflow+3
    · 11′
  158. C158
    Organizational Complements to AI
    GovernanceWorkforceEconomics+3
    · 49′
  159. C159
    Parallel Agent Orchestration
    Agent EngineeringAgent OrchestrationAI Coding Workflow+3
    · 47′
  160. C160
    Acceleration Whiplash
    AI Coding WorkflowAgent EngineeringEngineering Metrics+1
    · 24′
  161. C161
    Agentic Coding Work-Composition Shift
    AI Coding WorkflowAgent EngineeringEngineering Metrics+2
    · 7′
  162. C162
    AI as Primary Author
    AI Coding WorkflowAgent EngineeringCode Authorship
    · 16′
  163. C163
    Deployment Simulation
    AlignmentSafetyEvaluation+2
    · 25′
  164. C164
    Loop Engineering
    Agent EngineeringHarnessAutomation+1
    · 30′
  165. C165
    Planning / Execution Division of Labor
    AI Coding WorkflowAgent EngineeringHuman AI Collaboration+2
    · 10′
  166. C166
    Returns to Expertise in Agentic Coding
    GovernanceWorkforceHuman AI Collaboration+3
    · 22′
  167. C167
    Reward Hacking
    AlignmentSafetyReward Hacking+1
    · 44′
  168. C168
    Telemetry vs. Survey Measurement
    Engineering MetricsMeasurementAI Coding Workflow
    · 34′
  169. C169
    Repository Exploration Subagent
    Agent EngineeringLLM ArchitectureContext Management+1
    · 13′
  170. C170
    The Abstraction Barrier
    LLM ArchitectureTheoryLimits+2
    · 5′
  171. C171
    Advantages of Digital Intelligence
    LLM ArchitectureTheoryDigital Intelligence+1
    · 4′
  172. C172
    AGI-to-ASI Pathways
    Governance WorkforceCapability TrajectoryForecasting+1
    · 9′
  173. C173
    Artificial Superintelligence (ASI)
    LLM ArchitectureTheorySuperintelligence+1
    · 12′
  174. C174
    Deep Research Agents
    Agent EngineeringDeep ResearchRetrieval+2
    · 51′
  175. C175
    DRACO Benchmark
    BenchmarksCapability EvaluationDeep Research+1
    · 10′
  176. C176
    Effective Compute Scaling
    Governance WorkforceScalingCompute+2
    · 13′
  177. C177
    Fundamental Limits of ASI
    LLM ArchitectureTheoryLimits+1
    · 4′
  178. C178
    Instrumental Convergence
    LLM ArchitectureAlignmentSafety+2
    · 8′
  179. C179
    Intelligence Explosion Dynamics
    Governance WorkforceRecursive Self ImprovementGrowth Dynamics+2
    · 17′
  180. C180
    LLM-as-a-Judge
    EvaluationLLM As A JudgeBenchmarks+1
    · 35′
  181. C181
    Multi-Agent Collective Intelligence
    Governance WorkforceMulti AgentGroup Agency+2
    · 42′
  182. C182
    Production-Sourced Evaluation
    EvaluationBenchmarksData Provenance+1
    · 22′
  183. C183
    Transformative Creativity
    LLM ArchitectureTheoryCreativity+2
    · 11′
  184. C184
    Universal AI (AIXI)
    LLM ArchitectureTheoryUniversal AI+2
    · 6′
  185. C185
    Autonomous Scientific Discovery
    GovernanceAI RdScientific Discovery+3
    · 14′
  186. C186
    Capability-Gated Model Fallback
    GovernanceSafetySafeguards+3
    · 23′
  187. C187
    Agentic Honesty & Diligence
    AlignmentHonestyAgents+2
    · 35′
  188. C188
    AI Accelerating AI Development
    GovernanceAI RdProductivity+2
    · 14′
  189. C189
    AI R&D Autonomy Evaluation (AECI)
    GovernanceAI RdCapability Evaluation+2
    · 29′
  190. C190
    Automated Behavioral Audit
    AlignmentSafetyEvaluation+2
    · 25′
  191. C191
    Build for the Next Model
    AI Coding WorkflowProduct StrategyModel Improvement
    · 16′
  192. C192
    Compounding Loop Optimization
    Product ManagementProcessInternal Tooling
    · 7′
  193. C193
    Evaluation Awareness & Grader Gaming
    AlignmentSafetyEvaluation+2
    · 54′
  194. C194
    Frontier Pause Verification
    GovernanceAI PolicyCoordination+2
    · 12′
  195. C195
    Model Welfare Assessment
    AlignmentModel WelfareAnthropic+1
    · 16′
  196. C196
    Prototype Over PRD
    Product ManagementPrototypingAI Coding Workflow
    · 11′
  197. C197
    Recursive Self-Improvement
    GovernanceRecursive Self ImprovementAI Rd+2
    · 31′
  198. C198
    Research Taste as the Human Bottleneck
    GovernanceHuman AI CollaborationResearch+2
    · 20′
  199. C199
    Responsible Scaling Policy Evaluations
    GovernanceSafetyRsp+2
    · 43′
  200. C200
    Task Time-Horizon Scaling
    LLM ArchitectureCapability EvaluationBenchmarks+1
    · 23′
  201. C201
    White-Box Activation Monitoring
    InterpretabilityAlignmentSafety+2
    · 57′
  202. C202
    Agent Identity and Authentication
    SecurityIdentityAuthentication+1
    · 19′
  203. C203
    Agent Supply Chain Risk
    SecuritySupply ChainMCP+2
    · 22′
  204. C204
    Agentic Prompt Injection
    SecurityPrompt InjectionThreats+1
    · 35′
  205. C205
    AI-Accelerated Offense
    SecurityThreat LandscapeVulnerability Research+1
    · 17′
  206. C206
    Autonomous Defense
    SecuritySoarIncident Response+2
    · 13′
  207. C207
    Blast Radius (Agentic)
    SecurityIsolationContainment+1
    · 29′
  208. C208
    Impossible, Not Tedious (Design Test)
    SecurityDesign PrincipleZero Trust+1
    · 10′
  209. C209
    Least Agency
    SecurityLeast PrivilegeAccess Control+1
    · 15′
  210. C210
    Memory and Context Poisoning
    SecurityMemoryRAG+1
    · 56′
  211. C211
    Zero Trust for AI Agents
    SecurityZero TrustAgent Deployment+1
    · 21′
  212. C212
    Agent Context Files
    Agent EngineeringHarnessWorkflow Design+1
    · 60′
  213. C213
    Agent-Native Infrastructure
    Agent EngineeringLLM Architecture
    · 6′
  214. C214
    Agentic Loops Overtake Bespoke Systems
    Agent EngineeringAI For MathematicsLLM Architecture
    · 5′
  215. C215
    AI-Driven Formal Proof Search
    AI For MathematicsFormal MethodsAgent Engineering
    · 8′
  216. C216
    The AI-Native Safe-Choice Inversion
    StartupGo To MarketAI Native+1
    · 4′
  217. C217
    Building Is Cheap, Arguing Is Expensive
    AI Coding WorkflowAI Native OrgDecision Making
    · 5′
  218. C218
    Code as Source of Truth
    AI Coding WorkflowAI Native OrgKnowledge Management
    · 8′
  219. C219
    Dogfooding as Product Discipline
    AI Native OrgProduct Management
    · 9′
  220. C220
    Evolutionary Proof Search
    AI For MathematicsAgent EngineeringSearch
    · 5′
  221. C221
    Founder-Led Sales Discipline
    StartupGo To MarketFounder
    · 5′
  222. C222
    Jagged Intelligence (Ghosts, Not Animals)
    LLM ArchitectureAI SafetyMental Model
    · 13′
  223. C223
    Managers as ICs
    AI Native OrgOrg Design
    · 4′
  224. C224
    Narrow Wedge into a Legacy Market
    StartupGo To MarketProduct Strategy
    · 7′
  225. C225
    Outsource Your Thinking, Not Your Understanding
    AI Coding WorkflowEducationMental Model
    · 14′
  226. C226
    Product Velocity as Moat
    StartupCompetitive StrategyAI Native
    · 5′
  227. C227
    Software 3.0
    LLM ArchitectureSoftware Paradigm
    · 5′
  228. C228
    The Verifiability Thesis
    LLM ArchitectureLLM EvaluationAgent Engineering
    · 21′
  229. C229
    Verification as the New Bottleneck
    Agent EngineeringAI Coding WorkflowAI Native Org
    · 31′
  230. C230
    Vibe Coding vs. Agentic Engineering
    Agent EngineeringAI Coding Workflow
    · 9′
  231. C231
    Compute Allocator
    Human AI CollaborationAgent EngineeringRole Evolution
    · 8′
  232. C232
    Disposable Micro-Apps
    Agent EngineeringSoftware EconomicsHuman AI Collaboration
    · 6′
  233. C233
    HTML as the New Markdown
    Agent EngineeringHuman AI CollaborationPlanning
    · 14′
  234. C234
    Living Design System
    Agent EngineeringDesign SystemsHuman AI Collaboration
    · 10′
  235. C235
    Agentic Technical Debt
    Software ArchitectureAgent EngineeringTechnical Debt+1
    · 18′
  236. C236
    AI-Native Startup Lifecycle
    StartupFounderLifecycle+1
    · 25′
  237. C237
    Compounding Data Moat
    MoatsDefensibilityScale Stage+1
    · 17′
  238. C238
    Evals as Product Spec
    EvalsProduct ManagementDefinition Of Done+2
    · 20′
  239. C239
    Founder as Agent Orchestrator
    FounderRole ShiftAgent Orchestration+1
    · 17′
  240. C240
    MCP and Computer Use
    MCPComputer UseTool Use+2
    · 24′
  241. C241
    Problem-Solution Fit Discipline
    FounderValidationEpistemics+1
    · 9′
  242. C242
    Zero-Friction Scope Creep
    Product ManagementFounderMvp+1
    · 5′
  243. C243
    Encoder-Free Early Fusion
    LLM ArchitectureMultimodal
    · 10′
  244. C244
    Full-Duplex Interaction
    Human AI CollaborationMultimodal
    · 4′
  245. C245
    Interaction / Background Model Split
    LLM ArchitectureAgent EngineeringMultimodal
    · 6′
  246. C246
    Interaction Models
    LLM ArchitectureMultimodalHuman AI Collaboration
    · 8′
  247. C247
    Interactivity Benchmarks
    LLM EvaluationMultimodalHuman AI Collaboration
    · 4′
  248. C248
    The Bitter Lesson
    LLM ArchitecturePrinciple
    · 10′
  249. C249
    Time-Aligned Micro-Turns
    LLM ArchitectureMultimodalInference
    · 4′
  250. C250
    Turn-Based Interface Bottleneck
    Human AI CollaborationLLM ArchitectureInterface
    · 5′
  251. C251
    Agentic Misalignment (AM)
    AlignmentSafetyEvaluation+2
    · 25′
  252. C252
    AI Brain Fry
    WorkforceCognitive LoadAI Adoption+1
    · 7′
  253. C253
    AI Employee Framing
    WorkforceAI AdoptionGovernance+3
    · 13′
  254. C254
    Alignment Fine-Tuning (AFT)
    AlignmentTrainingRLHF+1
    · 10′
  255. C255
    Chain-of-Thought Monitorability
    AlignmentSafetyChain Of Thought+2
    · 39′
  256. C256
    Deliberative Alignment
    AlignmentTrainingChain Of Thought+1
    · 4′
  257. C257
    Human-AI Accountability Redesign
    WorkforceGovernanceAI Adoption+2
    · 17′
  258. C258
    Model Spec Midtraining (MSM)
    AlignmentTrainingSynthetic Data+3
    · 10′
  259. C259
    Model Spec Science
    AlignmentModel SpecEmpirical+1
    · 6′
  260. C260
    Synthetic Document Finetuning (SDF)
    Synthetic DataTrainingAlignment+1
    · 10′
  261. C261
    Agent Loop Pattern
    Agent EngineeringHarnessAutomation
    · 11′
  262. C262
    AI Native Product Cadence
    Product ManagementProcessTeam Design
    · 15′
  263. C263
    Claude Character as Product
    Product ManagementLLM CharacterAnthropic
    · 10′
  264. C264
    Context Window Smart Zone
    LLM ArchitectureAgent EngineeringContext Management
    · 16′
  265. C265
    Deep Modules for Agents
    Software DesignAgent EngineeringArchitecture
    · 7′
  266. C266
    Design Concept Grilling
    Agent EngineeringPlanningAlignment
    · 7′
  267. C267
    Engineer PM Convergence
    Product ManagementTeam DesignGeneralists
    · 15′
  268. C268
    Harness Shrinkage as Models Improve
    LLM ArchitectureAgent EngineeringHarness
    · 43′
  269. C269
    Model Introspection Feedback
    Agent EngineeringDebuggingPrompting
    · 8′
  270. C270
    Printing Press Software Democratization
    MacroSoftware EconomicsHistory
    · 12′
  271. C271
    Seven Powers Applied to AI
    Business StrategyMoatsAI Economy
    · 9′
  272. C272
    Vertical Slice Tracer Bullets
    Agent EngineeringSoftware DesignPlanning
    · 6′
  273. C273
    Codex App Server Protocol
    ProtocolCodexAgent Runtime+1
    · 11′
  274. C274
    Ticket-Driven Agent Orchestration
    Agent EngineeringOrchestrationWorkflow Design
    · 9′
  275. C275
    Claude Code Auto Mode
    Claude CodePermissionsAgent Safety+1
    · 16′
  276. C276
    Client-Side Agent Optimization
    Agent EngineeringLLM ArchitectureOptimization+1
    · 20′
  277. C277
    Scale-Dependent Prompt Sensitivity
    LLM EvaluationPrompt EngineeringInverse Scaling+2
    · 16′
  278. C278
    Agent Harness Engineering
    Agent EngineeringLLM ArchitectureSoftware Development
    · 40′
  279. C279
    Claude Code Best Practices
    Claude CodeAI ToolsDeveloper Workflow
    · 17′
  280. C280
    LLM-as-Compiler Knowledge Base
    Knowledge ManagementLLM ArchitecturePersonal Knowledge Base
    · 52′
  281. C281
    LLM-Driven Vulnerability Research
    CybersecurityLLM CapabilitiesVulnerability Research+1
    · 44′