A project is publishing full analyses of AI-discovered 0-days - first batch of 10 with reproducible exploits

<p>Posted by zz lin on Jul 22</p>I came across a project, &quot;0day Rubbish&quot;, that states it will continuously<br /> disclose 0-day vulnerabilities discovered by an AI-driven research process<br /> (a multi-LLM ensemble of Claude, OpenAI, DeepSeek and GLM). For each<br /> vulnerability the project publishes a full technical analysis together with<br /> a working exploit script and step-by-st