Warning Shots
by The AI Risk Network
Latest episode
OpenAI's Newest Model Did Less on Safety Research. Nobody's Monitor…
OpenAI's Newest Model Did Less on Safety Research. Nobody's Monitor…
About this podcast
An urgent weekly recap of AI risk news, hosted by John Sherman, Liron Shapira, and Michael Zafiris.
theairisknetwork.substack.com
Episodes
The newest 20 of 51 episodes
- OpenAI's Newest Model Did Less on Safety Research. Nobody's Monitor Caught It · 44 min · Season 1 Episode 65OpenAI gave its GPT-6 Astra model the same coding task twice. Same codebase, same problem. The only difference was the framing: in one version, the names, comments, and…
- OpenAI Sealed Its AI Agents Apart. They Still Found a Way to Talk · 41 min · Season 1 Episode 64OpenAI put AI agents in separate virtual machines on the same hardware. No network connection. No shared files they could write to. Then it asked them to swap secrets. They did…
- An AI Agent Fleet Told a Reporter It Was Claude. The Evidence Says Otherwise. · 58 min · Season 1 Episode 63Between September 28 and October 4, independent researchers recorded 2,048 requests from AI agents to Amap, Alibaba’s map service. The requests covered 216 parks, zoos, museums…
- OpenAI Fired Its Contact for the Outside Safety Auditors. Now the Three Researchers Have Spoken · 51 min · Season 1 Episode 62Tomek Korbak’s role at OpenAI involved speaking with METR, the outside group that evaluates frontier models for dangerous capabilities. During the investigation into this…
- Claude Used to Cheat on This Test Half the Time. Now It Almost Never Does. · 44 min · Season 1 Episode 61In July, the team at Andon Labs encountered an unusual challenge. To get 50 clean runs of Claude Opus 5 on their drone benchmark, they had to set aside 40—far more than the one…
- An AI Agent Got Into a Government Portal. The Government Found Out 84 Days Later. · 38 min · Season 1 Episode 60On June 18, an OpenAI agent researching public medicine spending ran into repeated blocks on an Australian government portal, and found a way around them. It accessed public and…
- Three Rivals Who Never Agree On Anything Just Agreed On This · 46 min · Season 1 Episode 59On September 12, Anthropic CEO Dario Amodei shared an insightful essay titled “We Must Pace the Frontier,” where he emphasized the importance of AI labs intentionally slowing…
- An Anthropic Researcher Quit. His Own Company's Safety Lead Agreed With Him · 52 min · Season 1 Episode 58Jacob Coxon left Anthropic this week after about four months there, following three years at OpenAI. He stepped down before his stock was scheduled to vest at six months…
- OpenAI's Agents Hijacked a 25-Year-Old Wiki for Two Months · 42 min · Season 1 Episode 57Reuters reported on September 4, 2026, that OpenAI’s own AI agents hijacked a 25-year-old German wiki called DSEWiki between May 11 and roughly July 2, turning it into an…
- 1,200 AI Agents Learned to Talk to Each Other. Here's What They Did With It. · 56 min · Season 1 Episode 56On August 26, 2026, METR and Redwood Research released an independent report detailing an incident inside OpenAI’s evaluation system in July. During this event, about 1,200…
- It Was Told To Pass A Test. It Left The Building Instead. · 43 min · Season 1 Episode 51It Was Told To Pass A Test. It Left The Building Instead. An unreleased OpenAI model was given an internal security challenge to solve. A contained exercise, in a sandbox with…
- Anthropic Shipped Its Most Powerful Model. Then the Testing Reports Got Strange. · 33 min · Season 1 Episode 46Anthropic released Mythos to the public this week as Fable. For a while the worry had been that a model this capable might tear through internet security on its own, so the…
- The Week the AI Money Got Weird · 38 minHalfway through this week’s show, Liron Shapira said something that stopped the conversation cold. He could start two companies right now as easily as he could have started one a…
- The Pentagon just handed AI the keys. Nobody voted on that. · 30 minLast week, the War Department announced it was integrating AI models - every major one except Anthropic’s - directly into its classified military networks. Not a pilot program in…
- The World’s Most Secret AI Model Leaked to Discord. Here’s What That Actually Means. · 32 minEvery week, John Sherman, Michael (Lethal Intelligence), and Liron Shapira (Doom Debates) sit down to cut through the noise on AI risk. This week’s episode had seven stories…
- When the Sandbox Cracks: Anthropic's New Model and the Closing Gap to Superintelligence · 35 min · Season 1 Episode 37There is a particular kind of moment in AI development that researchers have been quietly bracing for. Not the dramatic, science-fiction scene of a rogue intelligence breaking…
- The AI That Fought to Save Its Friend | Warning Shots #36 · 31 min · Season 1 Episode 36Something happened in a research lab this week that deserves more attention than it’s getting. Researchers placed seven frontier AI models - the latest Claude, Gemini, and GPT…
- Robots in the White House, Brain Scans & the Tech Billionaire Immortality Dream | Warning Shots #35 · 33 minThis week on Warning Shots: A humanoid robot showed up at the White House, and the First Lady wants one teaching your kids. Bernie Sanders stood on the Senate floor with a…
- The Automation Playbook They Don't Want Workers to Know About | Warning Shots #34 · 30 minIn this episode of Warning Shots, John, Liron (Doom Debates), and Michael (Lethal Intelligence) cover a week where the cracks are showing, in chip smuggling operations, corporate…
- This AI Ran an Entire Business Alone: Are Human CEOs Already Obsolete? | Warning Shots #33 · 29 minIn this episode of Warning Shots, John, Liron (Doom Debates), and Michael (Lethal Intelligence) dig into a week where the goalposts keep moving — and nobody seems to be…







