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

Writing, in order.

Pieces540Sections4Oldest10 Apr 2026Newest5 Oct 2026

Every article in the wiki, grouped by kind: Concept notes, Entity profiles, and Essay pieces. Hover any title for a preview; click to enter.

Filed under
allConceptEntityEssayIndex
Domain
agent systemsagent securityai coding practiceevals & benchmarksmodel capability & trainingalignment & safetyinterpretabilityinteraction & multimodalformal mathstartup & founderproduct & orgai economics & laborsuperintelligence trajectoryentities
Plate · 01 of 04
368
concept notes

Concept, in order.

Plate · 02 of 04
96
entity notes

Entity, in order.

  1. E01
    Jev
    EntityLLM ModelTyped Decisions+1
    · 7′
  2. E02
    Yoshua Bengio
    EntityPersonAlignment+1
    · 7′
  3. E03
    Claude Opus 5.5
    EntityModelAnthropic+1
    · 5′
  4. E04
    Google Threat Intelligence Group (GTIG)
    EntityOrgSecurity+1
    · 5′
  5. E05
    Irregular
    EntityOrgAI Evaluation+2
    · 5′
  6. E06
    Accenture
    EntityOrganizationConsulting+1
    · 6′
  7. E07
    Carta
    EntityCompanyData Source+2
    · 6′
  8. E08
    ICONIQ
    EntityCompanyData Source+2
    · 15′
  9. E09
    Ramp
    Type/entityEconomicsMeasurement
    · 8′
  10. E10
    Stanford Digital Economy Lab
    EconomicsWorkforceMeasurement+1
    · 8′
All 96 entity notes →
Plate · 03 of 04
60
essay pieces

Essay, in order.

  1. S01
    Adaptive Probing, Not Standardization: Splitting the Information Side of the AI-Interview Effect
    · 11′
  2. S02
    What the Agent-PR Oversight Numbers Can and Cannot Say
    DerivedCode ReviewAI Coding Workflow+2
    · 14′
  3. S03
    Is Self-GC's 0.3 Commit Threshold Portable? Re-Deriving the Cache-Break Break-Even
    · 9′
  4. S04
    Competitor-Indexed Safety Triggers: What the Revision Record Settles About Pause Postures, Acceleration Regret and Benchmark Perimeters
    DerivedGovernanceAI Policy+2
    · 15′
  5. S05
    Construct or Roster? What BEI's Entanglement Graph and IRT's Ability Ranking Are Measuring
    · 18′
  6. S06
    The Fable Gate: Who It Caps, and What in the Safety Case Is Independent of the Model
    DerivedSafetySafeguards+1
    · 11′
  7. S07
    Harness Patterns Under Scale and Domain Shift: Context Routing, Other Domains, Large Action Spaces, and the Overseer
    · 18′
  8. S08
    Rationale as a Dated Record: Where the Why Lives for the Next Reader
    DerivedAI Coding WorkflowKnowledge Management+2
    · 16′
All 60 essay pieces →
Plate · 04 of 04
16
index notes

Index, in order.

  1. I01
    Open Questions Dashboard
    · 21′
  2. I02
    Open Questions Backlog
    · 127′
  3. I03
    Evals & Benchmarks
    · 22′
  4. I04
    Interpretability
    · 6′
  5. I05
    Agent Security
    · 24′
  6. I06
    Agent Systems & Harness Engineering
    · 36′
  7. I07
    AI Coding Practice
    · 30′
  8. I08
    AI Economics & Labor
    · 21′
All 16 index notes →
Plate · #
486
subjects

By subject, most cited.

Agent EngineeringEntityEmpiricalAnthropicGovernanceAlignmentEvaluationAI Coding WorkflowLLM ArchitectureSecurityDerivedMeasurementSafetyBenchmarksWorkforcePersonHarnessHuman AI CollaborationEvaluation MethodologyEconomicsTest Time ComputeCode ReviewInterpretabilityCapability EvaluationPost TrainingStartupLLM As A JudgeMulti AgentAI For MathematicsContext ManagementLLM ModelMonitoringOpenaiOrgEngineering MetricsMultimodalVerificationAI Native OrgOpen WeightsProduct ManagementRecursive Self ImprovementAgent OrchestrationCapability TrajectoryCode QualityFailure ModesFounderPlanningPrompt InjectionReinforcement LearningAI PolicyFormal MethodsKnowledge ManagementClaudeConstruct ValidityCostThreatsGoogleOrganizationPromptingReward HackingTheoryThreat LandscapeAI CodingAI RdCalibrationFrontier LabsIncident ResponseOpen SourceOrg DesignReasoningAgentsAI EvaluationAI NativeClaude CodeCoding AgentsForecastingGovernance WorkforceIdentityLLM EvaluationMCPPsychometricsReference MonitorReliabilityResearcherReward DesignSupply ChainTrainingType/entityZero TrustAccountabilityAgentic RlAuthorizationChain Of ThoughtCoordinationCybersecurityEvalsInference ScalingMemoryRetrievalSafeguardsSearchSkillsSynthetic DataTechnical DebtTechnology DiffusionTool UseTrust BoundaryAdaptive EvaluationAI LabArchitectureAutomationCode GenerationCompanyDeceptionEnterprise DeploymentHonestyMethodologyMoatsModel WelfareOptimizationOrchestrationOversightPractitioner OpinionPrdProduct OrgProduct StrategyRole EvolutionStartupsTasteTeam DesignToolTraining GamingWorkflow DesignAgent DeploymentAgent HarnessAgent RuntimeAgent SecurityAI AdoptionAsiAuthenticationCase StudyCodingCognitive LoadCompetitive StrategyDeep ResearchDeploymentDesignDeveloper WorkflowDual UseEducationExpertiseGo To MarketHRIntegrationLaborLeast PrivilegeMacroMisalignmentPersonaProductProduct ProcessPropagationPrototypingProvenanceResearch MethodologyRspScalingSelf ReportSoftware EconomicsStanfordSuperintelligenceTestingTraining EfficiencyAccess ControlAdoptionAI ControlAI CoworkingAI Native OrganizationBelief ModificationBenchmark IntegrityCareerCatastrophic RiskClassifiersCode AuthorshipCodexCognitionCompetitive LandscapeComputeCoworkCredentialsData ContaminationData SourceData WallDeepmindDefense In DepthDefensibilityDiscoveryDocumentDocument ParsingEngineering LeadershipEquityGame TheoryGrowth DynamicsGtmHallucinationHuman CapitalIncentivesInferenceInterfaceInterpretability ResearcherIntrospectionLimitsLLM CharacterMental ModelMetrModelModel ImprovementModel RoutingModel SpecPermissionsPlatformPrivacyProbesProcessProduct ArchitectureProduct TasteProductionProductivityProtocolQualityQuantizationReasoning ModelsRed TeamingResearch ProgramRLHFScaling LawsScientific DiscoverySFTSoftware ArchitectureSoftware DesignStandardsSynthesisSystemTask SpecificationUniversal AIValue ModelVendorVendor ClaimVerifiabilityVulnerability ResearchY Combinator
+235 one-off subjects
AblationAbstractionAdaptive TestingAgencyAgent ArchitectureAgent FrameworksAgent SafetyAgent SkillsAgentic CodingAgentic EvaluationAgileAIAI EconomyAI EducationAI EthicsAI SafetyAI ToolsAixiAlignment ResearcherArms ControlArtifactsAsset PricingAuditingAuthorshipAutoformalizationAutonomyBenchmarkBenchmark ValidityBuild Vs BuyBusiness StrategyCapabilityCausal TheoryCharacterCLI AgentCoding AgentCollaborationCompetitionComplexity TheoryComputer UseConcept DiscoveryConfirmation BiasConfused DeputyConsciousnessConsultingContainmentContamination AdjacentContradictionControl PlaneCooperationCopyrightCourseCovert ChannelCreativityCredit AssignmentCultureData FlywheelData PipelineData ProvenanceDebate MapDebuggingDecision MakingDefenseDefinition Of DoneDefinitionsDelegationDelimiter InjectionDemocratizationDesign PrincipleDesign ProcessDesign SystemsDeterminismDeveloper EndpointDeveloper ExperienceDiffusionDigital IntelligenceDistillationDiversityDocumentationEconomic ImpactEconomic ModelingEconomistEfficiencyEmbodied AIEmergent BehaviorEmpirical SeEngineering IntelligenceEpistemicsError AnalysisExploit DevelopmentFailure ModeFaithfulnessFinanceFine TuningFormal VerificationFoundersFrontier LabGeneralistsGeneralizationGoodhartGoogle DeepmindGrounded TheoryGroundingGroup AgencyGrpoGuardrailsHardwareHciHierarchyHiringHistoryHouseholdHuman AI SubstitutionHuman In The LoopIncidentsInference CostInference EfficiencyInfluence OperationsInformation Flow ControlInfrastructureInput ValidationInstruction FollowingIntelligence MeasureInteraction MultimodalInternal ToolingInverse ScalingIsolationJailbreakKnowledge SharingLatent CapabilityLeaderboardsLearning GuideLeverageLifecycleLLM CapabilitiesLLM SimulationLong HorizonLoopsLow RankMarket DesignMarket ResearchMatrix CompletionMeasurement ValidityMechanistic InterpretabilityMediaMemorizationMessaging PlatformMetacognitionMethodMetricsMicrosoftMidtrainingMigrationMode CollapseModel CapabilityModel OrganismsModel PoisoningMultilingualMvpNational SecurityNetflixNous ResearchNvidiaOauthObservabilityOff HostOff Policy CorrectionOpen Ended DiscoveryOpinionsOrganizational TheoryOwaspPareto FrontierPersonal Knowledge BasePhilosophy Of SciencePlatform EngineeringPm SkillPolicyPrediction Powered InferencePrice TrendsPricingPrincipleProcurementProduction EvaluationPrompt EngineeringQualitative AnalysisRAGRelease DecisionsRepresentationsResearchResearch AgendaResearch AgentsResearch LabRevenue Per EmployeeReviewReward ModelingReward ModelsRl Post TrainingRole ShiftRubricsSafety EvaluationSandboxingScale StageShutdownSingularitySkills DevelopmentSoarSoftwareSoftware CraftSoftware DevelopmentSoftware ParadigmStatic AnalysisStatisticsSubagentsSuperpositionSurveillanceSystemsTalentTalent DensityTaxonomyTeam DynamicsTelemetryTest GenerationThird Party OversightThreat IntelligenceThreat ModelTool PoisoningTransparencyTyped DecisionsUncertaintyUnit EconomicsUnlearningValidationVenture CapitalVerbalized ConfidenceVersioningWorkflow