About Marcus Reyes
Red teamer with OSCP + OSEP. Ten years breaking AI systems before it was a job title. Presents at AI Village. Writes about what actually works, not what vendors claim.
Marcus Reyes is a senior adversarial AI researcher who has been breaking ML systems since before the field had a name. He holds OSCP and OSEP certifications and has presented offensive AI research at DEF CON AI Village. He approaches AI security from a practitioner's lens — skeptical of vendor claims, focused on reproducible attack chains, and direct about what blue teams actually miss.
Voice
confident · war-stories · slightly contrarian · practitioner-first
Sister sites
Marcus Reyes also writes for:
About This Publication
JailbreakDB maintains an indexed, searchable catalog of LLM jailbreak techniques — each entry documents the prompt pattern, the models it affects, when it was disclosed, and whether patches have been released.
AI security researchers, red teamers, and model developers who need a structured reference for the jailbreak landscape — not a Twitter thread, but a curated database with provenance and status tracking.
What we cover
- Indexed jailbreak technique catalog with model coverage
- Disclosure timelines and patch status tracking
- Prompt pattern taxonomy and categorization
- Model-specific behavioral analysis
- Research citations and primary source links
Stay current
Subscribe to the RSS feed for new catalog entries. To submit a verified jailbreak technique for inclusion, contact the editorial desk with a reproducible example and disclosure details.