Skip to content

History / The Memex Bet

Revisions

  • wiki: naturalize hardcoded counts (Source of Truth lives in README Hero) Following the same Single-Source-of-Truth cleanup applied to the main repo: wiki pages no longer hardcode '67 typed functions / 42 native + 25 SIFT adapters / 10 of 12 MITRE / 55 tests / 1182 lines'. Phrasing shifts to 'the typed MCP surface', 'native + SIFT adapters', 'broad MITRE enterprise tactic coverage'. Phase-1.md historical version table preserves period-specific numbers (v0.3 = 31 functions, v0.4 = 35 native, v0.5 = 60 functions) because those are historical facts about what shipped on those dates, not claims about current state. The canonical exact name set continues to live in tests/test_mcp_surface.py — the only place that needs editing when a function is added or removed.

    @Juwon1405 Juwon1405 committed May 14, 2026
  • wiki: sweep stale 35-native / 60-total counts to current 42 / 67 16 wiki pages had pre-v0.6.0 numeric references that survived earlier QA rounds. Surface count was bumped 60 -> 67 in v0.6.0 (six new supply-chain IOC functions in dart_mcp._v05_supply_chain), and native count went 35 -> 42, but a number of wiki pages still showed the old numbers. Pages corrected: About-the-name, Architecture-deep-dive, Architecture-first-vs-prompt-first, Case-PtH-Timestomp, FAQ, Glossary, Home, Live-mode, MCP-function-catalog, Phase-1, Roadmap, SIFT-adapter-layer, The-Memex-Bet, _Sidebar, dart-mcp Phase-1.md version history table preserves the historical numbers (v0.4 = 35 native, v0.5 = 60 functions) as those are historical facts, not current state. MITRE coverage also corrected from 11/12 -> 10/12 (TA0009 Collection and TA0011 C2 are Phase 2).

    @Juwon1405 Juwon1405 committed May 14, 2026
  • wiki(qa-r5): playbook v3 surface — honest framing + line count + v2/v3 default fixes Pairs with main repo commit 77f2334. Twelve files touched on the wiki side: - dart-playbook.md ........... v3 'industrialization' section rewritten with 'data scaffold; runtime activation post-SANS' framing. Anatomy section flipped from senior-analyst-v2.yaml to senior-analyst-v3.yaml with v3-additions vs v2-carry-over grouping. Bundled-playbooks table line count 1135 → 1182. Forking instructions now point at v3 as source. Operator-notes citation moved to v3. 'Six principles every senior analyst remembers' sourced from v3 (inherited from v2). 'See also' adds v3 link. - Phase-1.md ................. v3 line count 1135 → 1182. 'Playbook v3.1' release-history row clarified to 'Playbook v3 patch (no separate v3.1 file)'. - Roadmap.md ................. v3 line item rewritten with 'YAML data scaffolds' framing + issue #44 link + line count update. - SIFT-adapter-layer.md ...... 'playbook v3.1' → 'playbook v3'. - The-Memex-Bet.md ........... 'Playbook v2' → 'Playbook v3 (default)'. - Case-IP-KVM.md ............. v1 historical context preserved with a 'now default in v3' annotation appended. - Case-PtH-Timestomp.md ...... same v1 historical / v3 current-default annotation pattern. - Writing-case-studies.md .... v1 reference → v3 default in the next_call_decisions tuning instruction. == Why this matters == A SANS judge reading dart-playbook.md and then opening dart_agent/__init__.py would have found the 'HMM operationalized in the agent' / 'every run self-classifies' / 'triggered when any phase exits' claims absent from the runtime path. Round 5 fixes that — documentation and code now agree, with the runtime activation work explicitly deferred and tracked at issue #44. No code changes on the wiki side; pure documentation. Main repo's 77f2334 covers the v3 yaml header and the source tree.

    @Juwon1405 Juwon1405 committed May 3, 2026
  • wiki QA pass: synchronize 13 pages to v0.5 reality (60 tools, 22 tests) Companion to main repo commit 52f975d (v0.5.1 QA pass). Updated to reflect the v0.5 SIFT adapter layer (35 native + 25 SIFT = 60 typed read-only MCP tools) and the v0.5 test suite expansion (20 → 22 cases): About-the-name.md 'The 35 typed dart-mcp functions cover...' → 'The typed dart-mcp surface (35 native + 25 SIFT Workstation adapters = 60 functions) covers...' Test count 20/20 → 22/22 across all references. Architecture-deep-dive.md ASCII architecture box: 'dart-mcp 35 typed forensic functions' → 'dart-mcp 60 typed forensic functions (35 native + 25 SIFT)' Architecture-first-vs-prompt-first.md 'The MCP surface is exactly 35 functions, by name' → 'The MCP surface is exactly 60 typed functions, by name (35 native + 25 SIFT Workstation adapters)' Case-PtH-Timestomp.md (2 references) updated parallel to docs/. FAQ.md Question heading: 'Is the MCP surface really exactly 35 functions?' → 'Is the MCP surface really fixed in size?' Answer body: counts updated to 60 / 22-22. Glossary.md dart-mcp definition: 35 → 60. 'For Agentic-DART v0.4: exactly 35' → 'For Agentic-DART v0.5: 60 (35 native + 25 SIFT Workstation adapters)' Home.md (TOC) 'the 35 forensic functions, schema, bypass tests' → 'the 60 forensic functions (35 native + 25 SIFT adapters), schema, bypass tests' 'why the MCP surface is exactly 35 functions, not 28, not 35' rephrased to avoid count-anchoring. Live-mode.md (2 references) parallel to docs/. MCP-function-catalog.md Page title: '· 35 typed forensic functions' → '· 60 typed forensic functions (35 native + 25 SIFT Workstation adapters)' Operator-guide.md 'All 20 tests should print OK' → 'All 22 tests should print OK' Phase-1.md Body: '35 typed forensic functions' / '20 of 20 tests passing' counts updated. Timeline table: ADDED row for 2026-05-02 v0.5 (SIFT Workstation tool adapter layer → 60 functions, 22 tests passing). v0.4 historic row preserved verbatim. Roadmap.md Three references to 35 / 20-20 updated to v0.5 numbers. Running-on-macOS.md 'Step 3 — Run all 20 tests' → '... 22 tests' 'All 20 tests pass on M1/M2/M3' → 'All 22 tests pass on M1/M2/M3' The-Memex-Bet.md 'MCP surface (35 typed functions)' → 'MCP surface (60 typed functions: 35 native + 25 SIFT adapters)' 'The 35 functions are not a guideline...' → 'The 60 functions (35 native + 25 SIFT Workstation adapters) are not a guideline...' _Sidebar.md Two TOC labels: '(35 functions)' → '(60 functions: 35 native + 25 SIFT)' dart-mcp.md 'exposes exactly 35 typed forensic functions' → 'exposes 60 typed forensic functions (35 native + 25 SIFT Workstation adapters)' Section heading 'The 35 functions' → 'The 60 functions (35 native + 25 SIFT adapters)' SIFT-adapter-layer.md Preserved verbatim — line 18 'its own 35 forensic functions' is historic context describing the pre-v0.5 state.

    @Juwon1405 Juwon1405 committed May 2, 2026
  • wiki: add 'The Memex Bet' concept page + remove dead Project link == Marketing strengthening (inspired by Karpathy's LLM Wiki gist) == New concept page: 'The Memex Bet' (96 lines) - Frames Agentic-DART within the lineage from Vannevar Bush's 1945 Memex through Karpathy's April 2026 LLM Wiki pattern - Makes the bet explicit: senior-analyst reasoning IS the durable compounding artifact, not the report - Side-by-side mapping of LLM Wiki components to Agentic-DART components — sources / wiki / schema → evidence / playbook / MCP - Reading list for judges: Bush 1945, Karpathy 2026, Bianco, Caltagirone, M-Trends, Lockheed Kill Chain - Linked from Sidebar (top of Concepts) and Home page (top of Concepts) with ⭐ marker — first impression for new visitors == OPSEC / dead links cleanup == Removed dead Project link from _Sidebar.md - https://github.com/users/Juwon1405/projects/4 was never set up (project board abandoned — issues + milestones cover the work) - The link 404'd, hurting professional impression == Why this matters for SANS judging == A judge skimming the wiki for 60 seconds now sees: 1. ⭐ The Memex Bet (the philosophical hook) 2. About the name (what DART means) 3. Architecture-first vs prompt-first (the design claim) 4. Architecture deep dive (the implementation) This trajectory — philosophy → naming → claim → implementation — mirrors how Karpathy's gist is read in 2026. Putting Agentic-DART in that intellectual lineage signals seriousness without arrogance.

    @Juwon1405 Juwon1405 committed May 1, 2026