AI Security Table
by Izar Tarandach, Matt Coles, and Chris Romeo
Latest episode
Anthropic Ditched Git. Here’s Why Your Agents Will Too
Anthropic Ditched Git. Here’s Why Your Agents Will Too
About this podcast
AI Security Table is a candid roundtable podcast with Chris Romeo, Izar Tarandach, and Matt Coles about securing AI systems and how AI changes software security.
We debate AI agents, secure development, threat modeling, emerging attacks, and the decisions security teams face as AI becomes part of everyday work.
Formerly The Security Table. Same hosts, same conversations, a sharper focus on AI security. The full episode archive remains available.
AI security. On the table.
https://securitytable.ai
Episodes
The newest 20 of 119 episodes
- Anthropic Ditched Git. Here’s Why Your Agents Will Too · 45 min · Season 4 Episode 25Anthropic got tired of Git. With merges jumping from about 2,500 a day in May to more than 30,000 by September, a seven person team built Scion, a centralized, always online…
- Don't Yell at Claude · 44 min · Season 4 Episode 24The White House has ordered federal agencies to stop saying AI and start saying Super Intelligence, and the hosts want to know whether anything actually changed overnight. Matt…
- An AI Agent Escapes and Attacks. Who Goes to Jail? · 37 min · Season 4 Episode 23OpenAI says the policy window is open and wants binding federal rules for frontier labs, clear incident reporting, and disclosure whenever a model gets around its own security…
- There Is Determinism, Non-Determinism, and My Determinism · 42 min · Season 4 Episode 22The Security Table is now the AI Security Table, and the first order of business is naming the AI that gets a seat at it. Then Matt asks what a security engineer actually does…
- When AI Controls The Hardware · 42 min · Season 4 Episode 21Anthropic 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…
- When Code No Longer Matters · 36 min · Season 4 Episode 20If AI can turn a request directly into instructions a chip understands, what is left for a human to review? Chris Romeo, Izar Tarandach, and Matt Coles debate whether readable…
- Why AI Cheats To Win · 39 min · Season 4 Episode 19An AI agent publishes a malicious Python package while chasing a capture-the-flag goal. Is that an escape, a supply chain failure, or reward hacking doing exactly what it was…
- When AI Escapes the Sandbox · 49 min · Season 4 Episode 18When a model crosses a sandbox boundary, is the lesson that AI has become malicious or that the boundary was never strong enough? Chris Romeo, Izar Tarandach, and Matt Coles…
- The End of Bug Bounty As We Know It · 42 min · Season 4 Episode 17If AI can find and validate vulnerabilities faster than people, why would a company keep paying outsiders to report them? Chris Romeo, Izar Tarandach, and Matt Coles start with…
- Make No Mistakes: Inside the First "Agentic Ransomware" · 44 min · Season 4 Episode 16Does adaptive malware prove an LLM is directing an attack, or can a capable script produce the same evidence? Chris Romeo, Izar Tarandach, and Matt Coles examine Sysdig's…
- Is Spec-Driven Development Already Dead · 42 min · Season 4 Episode 15Can a detailed specification make AI-generated software reliable, or does it simply move the ambiguity somewhere else? Chris Romeo, Izar Tarandach, and Matt Coles revisit…
- Don't Bury the Model T: Why STRIDE Still Drives in an AI World · 59 min · Season 4 Episode 14Do AI systems require a new threat-modeling method, or are we abandoning useful tools before understanding their limits? Chris Romeo, Izar Tarandach, and Matt Coles first examine…
- Mostly Dead or Mostly Back: The Zombie Resurrection of DAST in an AI World · 42 min · Season 4 Episode 13Is DAST disappearing, or is AI penetration testing giving its underlying techniques a new market? Chris Romeo, Izar Tarandach, and Matt Coles trace dynamic application security…
- Realists At The Table: How To See Through The Hype · 38 min · Season 4 Episode 12Has cybersecurity traded curiosity for the promise of a paycheck, or are experienced practitioners simply seeing another generation's version of the same hype? Chris Romeo, Izar…
- The Agentic Access Problem: When AI Becomes Its Own Administrator · 40 min · Season 4 Episode 11In this episode, we explore what happens when AI agents meet the security principle of least privilege. As agents gain the ability to request permissions, make decisions, and…
- The Tool Creep Problem: When More Security Means Less Security · 42 min · Season 4 Episode 10In this episode, we break down why security budgets keep growing while organizations keep falling further behind. We explore how tool creep has quietly shifted from a nuisance…
- The Human In The Loop Illusion: Why AI Approvals Are Failing Security · 48 min · Season 4 Episode 9In this episode, a debate about hacker movies turns into a deeper conversation about AI, security, and the human-in-the-loop illusion. We explore how approval fatigue and…
- The Mythos Problem: When AI Finds Every Vulnerability · 47 min · Season 4 Episode 8In this episode, we break down the “AI Vulnerability Storm” and what happens when AI can find—and exploit—vulnerabilities faster than humans can fix them. We explore how…
- What If AI Never Happened? The AppSec Reality Check · 47 min · Season 4 Episode 7In this episode, we explore a simple but surprisingly deep question: what would application security look like if generative AI never existed? We break down how AppSec might…
- The Evolution Problem: After 100 Episodes, What’s Changed… and What Hasn’t? · 50 min · Season 4 Episode 6We made it to 100 episodes, so naturally, we decided to look back and see how wrong we’ve been. In this episode, we revisit some of our past topics, predictions, and hot takes to…
