This document brainstorms (and maps) how the attention / curiosity / drives stack applies across MathNN and every RL path in _AugmentedIntelligence. 1. MathNN applications Area How to apply layers Status / hook Dense / conv nets Use attention block outputs as features; curiosity weights which layer activations to read _Attention already in architectures; wire […]
Cognitive Layers (Attention, Curiosity, Drives)
Unified façade over MathNN attention/curiosity, RL intrinsic motivation, and cognitive-drive ODEs. Stack [text]Salience (candidates) → Attention (curiosity-biased) → Focus top-k ↑ ↑ weather/hazards β_eff from drives + bodyCuriosity (count + episodic mem) → intrinsic reward / shapeDrives ODE: attention, arousal, curiosity, fatigue, confidence Commands [text]layers status|doctor|metrics|selftestlayers mode task|explore|safety|sociallayers capacity 5 | beta 1.5layers link body […]
Child Psychology And Parenting RL
This subsystem integrates a child-psychology domain field and a parenting RL application into _AugmentedIntelligence. It is intentionally parent-facing and shadow-mode only. It does not diagnose a child, replace therapy or pediatric care, provide legal/custody advice, or autonomously message, direct, punish, discipline, or manipulate a child. Commands [powershell].\x64\Release\_AugmentedIntelligence.exe –command “child psychology status”.\x64\Release\_AugmentedIntelligence.exe –command “child psychology domains”.\x64\Release\_AugmentedIntelligence.exe […]
Features from this development chat — documentation index
This page is the table of contents for features designed and/or implemented in the conversation that produced Discovery→WordPress, IIS/PHP integration, TF32 GEMM, PHP graphs, Lua brainstorm glue, and the project changelog. # Feature Status Primary doc 1 Discovery journal → WordPress Implemented DiscoveryWordPress.md (DiscoveryWordPress.md) 2 IIS + PHP website integration MVP + design IisPhpIntegration.md (IisPhpIntegration.md) […]
Visual Studio build configurations
Project: _AugmentedIntelligence.vcxproj · toolset v145 · platform x64 (primary). Configurations Configuration GPU/CUDA TensorRT SIMD Llama build dir Preprocessor highlights **Debug \ x64** Toolkit present no default default Dev **Release \ x64** CUDA linked no default llama_build USE_CUDA, AI_MATHNN_LEARN, AI_REALITY_CONSTRUCT **Release-GPU-AVX512 \ x64** CUDA no AVX-512 llama_build USE_CUDA, AI_MATHNN_LEARN, AI_REALITY_CONSTRUCT, AI_MATHNN_LARGE **Release-GPU-AVX2 \ x64** CUDA […]
Brainstorm integrations (Lua + IIS/PHP + TF32 + Discovery)
Unifies features from this chat behind typed commands and Lua globals. Index of all chat features: ChatSession-Features.md (ChatSession-Features.md) Area Implementation Full doc Discovery → WordPress DiscoveryJournal + Lua discovery_* DiscoveryWordPress.md (DiscoveryWordPress.md) TF32 / matrix multiply CutlassAccel cuBLAS GemmEx TF32/FP32 + Lua cutlass_* TF32MatrixMultiply.md (TF32MatrixMultiply.md) PHP graphs graphs export → JSON; portal Graphs UI PhpGraphs.md (PhpGraphs.md) […]
Body equilibrium
Composes Coping regulation, weather load, reasoning status, and DCC write freeze into typed commands from the body/equilibrium brainstorm. Commands [text]body status|vitals|doctor|profiles|selftestbody profile restorative|work|sprint|recover|safebody equilibriumbody recover gentle|standard|hardbody freeze writes | body thaw writesday briefwatchdesk Profiles Profile Behavior restorative Rest; freeze DCC writes work Default sprint Allow heavier work recover After stress; freeze + coping safe Observe […]
Blender & Cinema 4D Bridges
Both DCC hosts share the same _AI pattern as Creo/Minecraft: strategy profiles, dry-run, recipes, BridgeManager adapters, and Plugin SDK façades. Offline mock scenes work without installing Blender or Cinema 4D. Related: PluginBridges.md (PluginBridges.md) · CreoIntegration.md (CreoIntegration.md) Blender (blender / blenderkit) Profiles Profile Strategy interactive Live bpy add-on / worker (UI open) headless blender -b -P […]
_AugmentedIntelligence System Map
High-level operator/developer map for _AugmentedIntelligence v11 (typed commands). Not a replacement for source code — first place to look when deciding what to run, configure, train, or extend. RL hub: ReinforcementLearning.md (ReinforcementLearning.md) Core Runtime local/network control. Common checks: [text]settings showsocket statusdeveloper commands Agents And Autonomy WindowsServerAgentFleet.*, Application Support agents. RSI and Minecraft […]
_AugmentedIntelligence Agent Orchestration
This document covers the unified agent … command namespace added around the existing native and Lua-backed agents. Related docs: What Was Added Core Commands [text]agent helpagent registryagent profilesagent profile show <profile>agent profile apply <profile> [dry-run]agent listagent status [agent]agent start <agent>agent stop <agent|all|type <type>>agent pause <agent>agent resume <agent>agent restart <agent>agent configagent config max_concurrent <count>agent rl statusagent […]