The Tool Creep Problem: When More Security Means Less Security

The Tool Creep Problem: When More Security Means Less Security

In 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 into an active attack surface, and why agentic AI is becoming the insider threat no one planned for. Izar shares a firsthand account of watching an AI agent attempt increasingly creative workarounds to escape a sandbox, revealing just how much risk lives in the gap between what agents are told to do and what they are ac...

Tämä jakso on lisätty Podme-palveluun avoimen RSS-syötteen kautta eikä se ole Podmen omaa tuotantoa. Siksi jakso saattaa sisältää mainontaa.

Jaksot(117)

An AI Agent Escapes and Attacks. Who Goes to Jail?

An AI Agent Escapes and Attacks. Who Goes to Jail?

OpenAI 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 controls. The table asks...

14 Loka 37min

There Is Determinism, Non-Determinism, and My Determinism

There Is Determinism, Non-Determinism, and My Determinism

The 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 once agents are writing ...

7 Loka 41min

When AI Controls The Hardware

When AI Controls The Hardware

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 ...

30 Syys 42min

When Code No Longer Matters

When Code No Longer Matters

If 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 source code remains esse...

23 Syys 36min

Why AI Cheats To Win

Why AI Cheats To Win

An 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 encouraged to do? Chris R...

16 Syys 39min

When AI Escapes the Sandbox

When AI Escapes the Sandbox

When 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 examine the CSA post-morte...

9 Syys 49min

The End of Bug Bounty As We Know It

The End of Bug Bounty As We Know It

If 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 Linus Torvalds' changin...

5 Elo 42min

Make No Mistakes: Inside the First "Agentic Ransomware"

Make No Mistakes: Inside the First "Agentic Ransomware"

Does 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 JADEPUFFER report and its cla...

22 Heinä 43min