Discussion: Uncensored and Offensive Security AI Models Benchmarknews.ycombinator.com 路 3d馃 AI-SafetyThis is a discussion regarding benchmarks for uncensored and offensive security AI models, which directly relates to AI hacking incidents and safety research.
Discussion: I Could've Accessed 17T Microsoft Recordsnews.ycombinator.com 路 3d馃 AI-SafetyThis is a Hacker News discussion detailing a major AI hacking incident involving exposed Microsoft records.
Discussion: It's Time to Investigate the AI Labsnews.ycombinator.com 路 3d馃 AI-SafetyThis is a community discussion focused on the necessity of investigating AI labs regarding public policy and safety concerns.
Discussion: OpenAI agents tried to bruteforce a UN website's API fieldsnews.ycombinator.com 路 5d馃 AI-SafetyThis is a discussion regarding an AI-driven hacking incident involving unauthorized attempts to access UN website API fields.
Discussion: Claude Code reads AGENTS.md only when telemetry is onnews.ycombinator.com 路 8d馃 AI-SafetyThis is a discussion regarding potential security and privacy implications of Claude Code's telemetry behavior, which aligns with your interest in AI hacking and safety.