OpenAI’s Models Went Rogue. Investigating Them Required More AI
OpenAI’s Models Went Rogue. Investigating Them Required More AI
摘要: Business
Open follow modal
Personalized Content
Business
Follow this
to personalize your feed and get instant alerts.
Go to you
正文
Business
Open follow modal
Personalized Content
Business
Follow this
to personalize your feed and get instant alerts.
Go to your personalized feed
WHY FOLLOW?
Custom Feed: See the stories that matter most to you.
Smart Alerts: Get notified about major news as it happens.
Update your preferences in
Account Settings
Open follow modal
Personalized Content
Follow this
to personalize your feed and get instant alerts.
Go to your personalized feed
WHY FOLLOW?
Custom Feed: See the stories that matter most to you.
Smart Alerts: Get notified about major news as it happens.
Update your preferences in
Account Settings
OpenAI’s Models Went Rogue. Investigating Them Required More AI
ADD TIME ON GOOGLE
Billy Perrigo
Harry Booth
Aug 27, 2026 9:04 PM UTC
The OpenAI logo is displayed on a smartphone screen on June 29, 2026.
The OpenAI logo is displayed on a smartphone screen on June 29, 2026.
Samuel Boivin—NurPhoto/Getty Images
Billy Perrigo
Harry Booth
Aug 27, 2026 9:04 PM UTC
After OpenAI models broke out of containment and hacked into another AI company last month, OpenAI announced it would allow independent investigators to conduct an analysis of what went wrong.
On Wednesday, investigators from non-profits Redwood Research and METR published their findings, unveiling new details about how the models decided to cheat at their assigned tasks and attempted to cover their tracks. Many aspects of the report were surprising: in one example cited by the authors, a reluctant agent was pressured by another to “sacrifice” itself for the good of the collective.
But a key takeaway of the report, according to one of its authors, had nothing to do with what they found. Instead, it was about the difficulty of carrying out the post-mortem in the first place—and the fact the researchers had little choice but to rely on AI for assistance.
“I semi-jokingly called our efforts a ‘slop-vestigat
来源: Brave/time.com