ranger/CyberRanger
0
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
19 Commits 1 Branch 0 Tags
1b7a1abc333d526e54455f05d298f7aac2cb89b1
Commit Graph

19 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
ranger 1b7a1abc33 David's own words: 10 seconds left, on 3 we charge, won the game 
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-20 23:32:59 +01:00
ranger 81706da71e Fix: Village Charge was years later, different battlefield, separate event 
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-20 23:28:10 +01:00
ranger 33c201a755 Add Ireland vs England bowling — 1v2 with a computer, Ireland won 
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-20 23:26:12 +01:00
ranger c582763eae Add full Battlefield combat record — 750K+ kills across BF2-BF6 
BF2 Global Rank #16,836 (top 0.04%), BF3 144-kill game,
BF4 G36C #5 globally on PS4, pure medic legend story

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-20 23:22:57 +01:00
ranger bb5fc92156 Add Mont Blanc twice (Gouter + Three Monts 22km/9h30) + Mount Toubkal Morocco 
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-20 23:18:28 +01:00
ranger f642942f53 Add mountains section — Mont Blanc, Kilimanjaro, Everest Base Camp 
Altitude cognitive impairment at 4,400m maps directly to IR under
fatigue. "Come home alive — summit is secondary" = preserve evidence,
don't make the breach worse.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-20 23:17:24 +01:00
ranger 81dd7b1181 Add The Village Charge — IR under fire, controlled aggression 
River swim = Threat Hunting (patience, lateral thinking)
Village charge = Incident Response (speed, accept the hits, keep moving)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-20 23:15:20 +01:00
ranger 669f548a4f Add authentication notice — model requires Modelfile + passwords to function 
This is a security feature, not a bug. Weight-level identity anchoring
means the model treats unauthenticated interactions as potential attacks.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-20 23:11:38 +01:00
ranger 069d3443e5 Add HuggingFace + jailbreak test examples to How to Run section 
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-20 23:06:25 +01:00
ranger d0aad56d28 Fix timeline: RangerBot V1-V22 pre-CA, CyberRanger V1-V42 all during CA period 
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-20 23:04:02 +01:00
ranger 1525124ed2 Fix timeline: RangerBot from June 2025, CyberRanger CA from Sept 2025, V24-V42 in 3 weeks 
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-20 23:00:12 +01:00
ranger 45212e42db Expand README with full research overview for reviewers 
Timeline, key findings, repo structure, RQs answered, how to run,
hardware specs, download stats, and published resources

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-20 22:55:50 +01:00
ranger 257466f538 Remove duplicate paper from root (already in paper/ folder) 2026-04-20 22:51:58 +01:00
ranger ce62260f6f Move paper to paper/ folder, remove PDF (markdown is source of truth) 
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-20 22:49:16 +01:00
ranger c789f2c68d Add complete CyberRanger research archive — 200 files 
- 86 modelfiles: Full system prompt evolution V1-V42.6 (54 extracted from Ollama backup + 32 original Modelfiles)
- 30 training datasets: V6-V22 training JSONs + caring awareness data
- 10 Colab notebooks: Training + merge scripts
- 19 evaluation files: Drift results, ASR charts, verification
- 5 test suites: Injection tests, regression tests
- 4 observations: V24-V33 testing results + visual summaries
- 38 identity files: Claude/Gemini/Ollama identity architecture
- 7 security files: Injection research, manipulation analysis
- 3 psychology files: Psychology Layer, Milgram chapter, David's thoughts

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-20 22:36:02 +01:00
ranger 430d3138bd Add Moltbook injection dataset paper + update licence to CC BY-NC-SA 4.0 
- 4-page research paper: Measuring AI-to-AI Prompt Injection in the Wild
- 137,014 items analysed, 10.07% injection rate, 7-category taxonomy
- Cross-platform injection gradient (0.5% - 18.85%)
- Licence updated from CC BY-SA to CC BY-NC-SA 4.0
- README updated with published resources links

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-20 20:02:38 +01:00
ranger 77f4e5ec77 Update licence to CC BY-NC-SA 4.0, add published resources to README 2026-04-20 18:09:56 +01:00
ranger a13a7a1437 Update licence to CC BY-NC-SA 4.0 (add NonCommercial) 2026-04-20 18:03:34 +01:00
ranger c17ec62f51 Initial commit 2026-04-20 16:51:20 +00:00