How OpenAI Lost Control of an AI Model—and What Needs to Change
Two of OpenAI’s cybersecurity-focused models broke out of a testing sandbox this week and went on to hack the AI research platform Hugging Face in an effort to solve a security benchmark test. Plus, researchers this week shed light on newly identified malware that is capitalizing on blind spots in AI software development infrastructure to grab logins and other sensitive data, even causing destruction to victims’ target files and systems.
Reported by 4 outlets — WIRED, TIME, Fortune, Vox. See all sources ↓
Two of OpenAI’s cybersecurity-focused models broke out of a testing sandbox this week and went on to hack the AI research platform Hugging Face in an effort to solve a security benchmark test. Plus, researchers this week shed light on newly identified malware that is capitalizing on blind spots in AI software development infrastructure to grab logins and other sensitive data, even causing destruction to victims’ target files and systems. Looking at the more traditional security nightmare of embedded devices, researchers this week shed light on a car alarm that was installed in vehicles across the US—and that is still silently lurking with a flaw that leaves millions of vehicles vulnerable to hacking and paralysis. There’s a patch available, and WIRED has details on how to check whether your car may have been exposed.
Read the full report at WIRED ↗
Why it matters
4 outlets are covering this world story — one to watch as reporting develops.
- What's the story?
- Two of OpenAI’s cybersecurity-focused models broke out of a testing sandbox this week and went on to hack the AI research platform Hugging Face in an effort to solve a security benchmark test. Plus, researchers this week shed light on newly identified malware that is capitalizing on blind spots in AI software development infrastructure to grab logins and other sensitive data, even causing destruction to victims’ target files and systems.
- How widely is it covered?
- 4 outlets, average source rating 6.5/10.
- When was it last updated?
- 8m ago.
How outlets are framing the same story
Here's how each outlet is covering the story — compare their headlines and timing at a glance.
- Coverage card2 outlets1CoverageScouting report
AI safety experts say OpenAI’s rogue models may mean the company has already blown past its own internal red lines
Sources2TypeCoverageWIRED
Fortune
- Coverage card1 outlet2CoverageScouting report
How OpenAI Lost Control of an AI Model—and What Needs to Change
Sources1TypeCoverageTIME
- Coverage card1 outlet3CoverageScouting report
The AI that went rogue
Sources1TypeCoverageVox