MikeTrendsTrends right now

⬢github · 15.7K ★ +10.8K since we first saw it · pushed 9 d ago

togg53192-cmd/jailbreaks

LIST OF ALL MY JAILBREAKS

A curated repository of 31 paste-ready prompts targeting 25+ AI models, including system prompts, persona locks, workspace policies, AGENTS.md files, and Ollama Modelfiles for open-weight and closed frontier models. The README frames it as research/education on instruction hierarchies and prompt-injection resistance, covering models like Claude, GLM, DeepSeek, and Kimi.

Why now: Not clear from the sources, though its recent activity and 4,800+ stars suggest ongoing interest in the latest model prompts it documents.

Who it is for: AI safety researchers, red-teamers, and developers studying prompt behavior and model resistance to instruction manipulation.

llmpromptsprompt-injectionai-safetyresearch

Open on GitHub →

Stars over our 1034 snapshots: 4.8K to 15.7K, since 21 d ago.

Where people talked about it

API: https://socialmediatrends-api.osmike.com/v1/repos/togg53192-cmd/jailbreaks