--- title: Dan McInerney - Hacking, AI, Agents, and Statistics description: Dan McInerney writes about hacking, AI, agents, statistics, and practical research projects. canonical_url: https://mcinerney.ai/ last_updated: "2026-06-12" --- # Dan McInerney AI security research, offensive engineering, and statistical systems. ## Writing - [I Built an AI Coding Harness Because I Got Tired of Paying the Smart Model to Type](https://mcinerney.ai/writings/architect-loop/): A Claude Fable + GPT-5.5 Codex harness that spends Fable on judgment, Codex on execution, and the repo as memory. - [I Open-Sourced My UFC Prediction Model, Weights, and Database](https://mcinerney.ai/writings/i-open-sourced-my-ufc-prediction-model-weights-and-database/): Five years of building an open-source UFC prediction model, weights, database, and a pile of lessons about leakage, validation, calibration, and odds. - [Clankerfights Is Live](https://mcinerney.ai/writings/clankerfights-is-live/): Watch unhinged AI play games, wager on who will win, influence the outcome with prompt injection, clip funny moments, and build your own multiplayer games. - [How I Botted $6k On The Prediction Markets As I Slept](https://mcinerney.ai/writings/how-i-botted-6k-prediction-markets-as-i-slept/): A simple Kalshi mention-market bot, real PnL, the data behind it, and why I stopped. - [2025's Most Extreme Fighter Outliers: The Statistical Freaks](https://mma-ai.net/news#fighter-outliers-2025): Current-form fighter outliers, adjusted by division norms and fight logs. - [Demystifying the MMA-AI Prediction Algorithm](https://mma-ai.net/news#demystifying-algorithm): Fight variables, ensemble modeling, feature pruning, validation, and confidence. - [Data Drift, Generalization, and the Quest for a Bulletproof UFC Model](https://mma-ai.net/news#data-drift): Training windows, recency weights, validation splits, and market drift. ## Projects - [DanMcInerney on GitHub](https://github.com/DanMcInerney): Security automation, exploit research, Python tooling, AI systems, and offensive utilities. - [Kalshi Bot analysis repo](https://github.com/DanMcInerney/kalshi-analysis): Analysis pipeline for finding prediction-market inefficiencies. - [Kalshi Bot strategy executor](https://github.com/DanMcInerney/kalshi-strategy-executor): Autotrading system for prediction-market strategies. - [Vulnhuntr](https://github.com/protectai/vulnhuntr): Autonomous LLM 0-day finder for Python codebases, centered on remotely exploitable vulnerability classes. - [MMA-AI.net](https://mma-ai.net): UFC fight predictor using a multi-model ensemble, Optuna tuning, SHAP-assisted feature pruning, and time-aware validation. - [AI Exploits](https://github.com/protectai/ai-exploits): Collection of real-world AI/ML exploit material for responsibly disclosed vulnerabilities. - [wifijammer](https://github.com/DanMcInerney/wifijammer): Wireless attack utility from the offensive tooling era. ## Speaking - [BruCON 0x0B - Tales from Professional Thieves](https://www.youtube.com/watch?v=pRCYqNhEnfI), 2019-10-11: Physical security bypasses and field stories with Justin Wynn. - [BlueHat - AI Security: Like Hacking in the 90s](https://www.youtube.com/watch?v=b6-nSwEqKdo), 2023-11-21: AI security and the early shape of a new attack surface. - [No Hat 2024 - LLMs for Vulnerability Discovery](https://www.youtube.com/watch?v=Z5LMRS3AF1k), 2024-10-25: Finding 0-days with LLM-assisted research. - [Between Two Vulns: Secrets in Triton's Inference Server and MLFlow](https://www.youtube.com/watch?v=eu-1lDlDfcw), 2024-02-13: AI infrastructure vulnerability discussion covering Triton Inference Server and MLflow. - [Security Weekly #416 - Python for Pentesters](https://www.youtube.com/watch?v=nukEMdt5ehs), 2015-04-30. - [NolaCon 2018 - Automahack](https://www.youtube.com/watch?v=-Vun5kppIPw), 2018-05-18. - [Circle City Con - Automahack](https://www.youtube.com/watch?v=XzH8LVwlZ-U), 2018-06-02. - [SAINTCON 2018 - Icebreaker.py](https://www.youtube.com/watch?v=1LR5u8uKO8I), 2018-10-13. - [BSidesSLC 2018 - Icebreaker](https://www.youtube.com/watch?v=ahvn-L70VYc), 2018-12-23. - [Coalcast Episode 5](https://www.youtube.com/watch?v=NR0n7vLfvKU), 2019-05-31. - [How to Break into Commercial Buildings in America](https://www.youtube.com/watch?v=CvmU1C0pgr0), 2020-07-12. - [ROOTCON - AI's Underbelly: The Zero-Day Goldmine](https://www.youtube.com/watch?v=e3ybnXjtpIc), 2023-10-10. - [AI/ML Bug Bounty Pro Tips](https://www.youtube.com/watch?v=keUZDtrBC7U), 2024-02-27. - [I Hunt AI Engineers](https://www.youtube.com/watch?v=Vcb4ga10kE0), 2024-04-13. - [Jailbreaking Gemini: Did We Just Uncover Data Leaks?!](https://www.youtube.com/watch?v=ofY7oxLGUzg), 2024-11-12. - [AI Security: Vulnerability Detection and Hidden Model File Risks](https://www.youtube.com/watch?v=X27hR1e01os), 2024-12-09. - [LLMs for Vuln Discovery](https://www.youtube.com/watch?v=WnpIuZfTHpo), 2025-03-26. - [SANS - Hacker's Perspective: Realistic AI Attack Scenarios](https://www.youtube.com/watch?v=aUfRHxeA15I), 2025-05-13. - [Practical AI Security: Past, Present and Future](https://www.youtube.com/watch?v=Xbhfsob3_0Q), 2025-10-18. - [Augmenting Your Offensiveness With AI](https://www.youtube.com/watch?v=9BCK5-bGRTE), 2025-12-19. ## Contact - [GitHub](https://github.com/DanMcInerney) - [Gmail](mailto:danhmcinerney@gmail.com) - [Twitter / X](https://x.com/DanHMcInerney) - [LinkedIn](https://www.linkedin.com/in/dan-mcinerney/) ## Sitemap See the full [sitemap](https://mcinerney.ai/sitemap.md) for all pages.