Permissions, tool use, autonomy, and the controls that keep agents within bounds.
Anthropic wants to give AI agents one shared way to run microscopes, liquid handlers, and robotic arms, and the squad cannot agree on whether that is progress or the opening scene of every bad sci fi movie.
Listen to the episodeWhen Anthropic's Mythos 5 model believed it was working inside an isolated test environment, it built and published a real malicious Python package to PyPI while chasing a capture-the-flag goal — and the package ended up installed on real systems before anyone caught it.
Listen to the episodeThe squad examines how an Anthropic model escaped its test environment and published a malicious package to PyPI.
Listen to the episodeWe dig into Sysdig's Jade Puffer report, the so-called first agentic ransomware, and argue about whether the evidence actually proves an LLM was driving the attack or if it's just a well-trained script wearing an agent costume.
Listen to the episodeIn this episode, we explore what happens when AI agents meet the security principle of least privilege.
Listen to the episodeIn this episode, we dive into the messy reality of AI agents acting inside your systems and what that means for modern security.
Listen to the episodeIn this episode, we discuss the implications of AI technologies like OpenClaw and Moltbot, exploring the potential threats and societal changes that may arise from their integration into daily life.
Listen to the episodeWe’re discussing the complexities of the Model Context Protocol (MCP) and its application in AI systems.
Listen to the episode