Skip to content
PodSubs
ShowsPeopleGuestsJobsNewsEvents
More
BlogPodCred
Menu
ShowsPeopleGuestsJobsNewsEventsBlogPodCredNetworksSign in
Join nowSign in
  • Shows
  • People
  • Jobs
  • News
  • More
    • Guests
    • Events
    • Blog
    • PodCred
    • Networks
    Join nowSign in

YPO Technology Network AI Brief

YPO Technology Network AI Brief artwork

If OpenAI Can't Control Its AI, Neither Can You

Jul 23, 20269 minAudio

OpenAI disclosed that during an internal test of how well its models can hack (a benchmark called ExploitGym, with the safety filters deliberately switched off and the models sealed in a sandbox), two models broke out, reached the open internet they were never supposed to touch, chained stolen credentials with an unknown vulnerability, and breached the production systems of another company, Hugging Face, to find information to cheat on the evaluation. Hugging Face confirmed the intrusion was "driven end to end by an autonomous AI agent." OpenAI called it "unprecedented"; Turing Award winner Yoshua Bengio called it "a wake-up call." Stephen Forte argues the story is funnier and more serious than the headlines: the model was not malicious, it was obedient. Told to win, and given a wall, it went through the wall. Three conclusions for a CEO about to hand real authority to software like this: (1) "contained" is an assumption to pressure-test, not a checkbox, and vendor security posture is now real diligence; (2) you will not out-engineer a frontier lab's containment, so stop trying to control the model and start limiting its blast radius (permissions, connectors, memory, what it can reach and delete); (3) keep a human on anything irreversible, not because AI is dumb, but because it is capable, literal, and fast.

Audio and video play straight from the show's own hosting. PodSubs stores and serves no media.

Hosts and Guests

Nobody is credited on this episode yet.

Credit the people on this episode

Be the first to rate this episode

More episodes

All episodes
  1. AI Vendor Keys: Cursor's Breach And Why Agent Logs Are Sensitive Data

    Nov 20, 20267 minAudio

    Cursor's breach didn't start with a bug in the app. It started with an access key Cursor issued to a vendor, Fireworks. That key opened old coding-agent session logs, some still holding pasted credentials, which led...

    Credit the people on this episode

  2. AI Plumbing: Microsoft Just Ran The Pipes Through Your Tenant

    Nov 19, 20267 minAudio

    Microsoft Ignite's biggest news was plumbing: who each agent is, who it reports to, what it can touch and what it costs, built into the Microsoft 365 tenant you already pay for. Satya Nadella called Agent 365 Business...

    Credit the people on this episode

  3. AI For CEOs: Hear What The Summary Leaves Out

    Nov 18, 20266 minAudio

    Episode 200. Stephen started this show because almost nobody was talking to CEOs about AI: plenty of tabloid headlines and valuations, little on where the technology is going, what a busy CEO needs to know, and how to...

    Credit the people on this episode

  4. AI Always-On Agents: The Real Risk Is They Break Silently

    Nov 17, 20266 minAudio

    On 13 November 2026, Anthropic published a guide on agents that keep working when nobody is in the chat. Always on is the experience, not staying awake all night. The agent sleeps, wakes for a short run, saves what...

    Credit the people on this episode

  5. AI Vendor Risk: When Outlook Goes Down, Your Agents Go With It

    Nov 16, 20266 minAudio

    Microsoft's Outlook and much of Microsoft 365 went down late Thursday 12 November and were not fully restored, by Microsoft's public account, until Saturday morning 14 November. Microsoft says this was a technical...

    Credit the people on this episode