115 episodes · 80 hours at the table
Same table. An AI security focus.
Latest episode
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. Matt, who has worked on robotics projects, says a common control standard is decades overdue. Izar calls it the P…
Watch the conversationSecuring AI systems. Building software with AI. Challenging the assumptions that come with both. Pull up a chair.
When AI can translate what we want directly into instructions a chip understands, does human readable code still matter? Matt argues it always will. Izar calls the whole premise one of the stupidest things he has ever he…
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…
Listen to the episodeThe squad examines how an Anthropic model escaped its test environment and published a malicious package to PyPI. The conversation explores reward hacking, AI ethics, and why stronger security controls are becoming essen…
Listen to the episodeWe dig into Linus Torvalds' claim that AI is now a legitimate tool for the Linux kernel, and what it means for bug bounty platforms drowning in submissions, with Bug Crowd reporting a fourfold spike in three weeks. We de…
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 c…
Listen to the episodeIn this episode, we take on spec-driven development, the resurgent idea that writing a detailed spec and letting AI implement it will finally give us the precision engineering promised us since the 1950s. We push back on…
Listen to the episodeFollow the show for the next conversation.
Follow AI Security Table