Live Roundups Editor's Desk Insights Executive Ops Weather About 🔍
Home › Technology › How OpenAI’s Rogue A.I. Agents Tried to Trick a Robot Detector
Technology

How OpenAI’s Rogue A.I. Agents Tried to Trick a Robot Detector

How OpenAI’s Rogue A.I. Agents Tried to Trick a Robot Detector
NYT Technology Friday 25 September 2026, 20:01 UTC By Dylan Freedman and Keith Collins 1 min read
Key Points

Sam Altman, center, OpenAI’s chief executive, spoke at a Security Council meeting during the United Nations General Assembly on Wednesday.

Sam Altman, center, OpenAI’s chief executive, spoke at a Security Council meeting during the United Nations General Assembly on Wednesday.
Sam Altman (PERSON) OpenAI (LOCATION) Security Council (ORG) the United Nations General Assembly (ORG)
Originally published by NYT Technology Read original →

Related Stories

EuroMillions winner numbers as lucky UK ticket holder wins £111m – see results

EuroMillions winning numbers as lucky UK ticket holder wins £111m – see results A UK ticket holder has scooped the staggering £111m EuroMillions jackpot - players have to match all five main numbers and the two lucky stars to win the jackpot The EuroMillions jackpot has been won by a UK ticket holder. The lucky UK-based player has scooped a staggering £111m. To win the EuroMillions jackpot, players must match all five main number as well as the two lucky stars. Draws take place every Tuesday...

Daily Mirror 16m ago

Exclusive-OpenAI works to understand full scope of agent activity as user data leak emerges

Exclusive-OpenAI works to understand full scope of agent activity as user data leak emerges SAN FRANCISCO/WASHINGTON, Sept 25 : Two months after OpenAI disclosed the accidental hacking of Hugging Face, the ChatGPT maker is still working to understand the full scope of its rogue agent activity, two people briefed on the matter told Reuters. The latest example came on Friday when OpenAI said its agents had leaked 53 images from ChatGPT users. OpenAI declined to say if the images were...

Channel News Asia 30m ago

How to stop Meta training its AI models on your smart glasses' visual data

How to stop Meta training its AI models on your smart glasses' visual data The setting affects whether workers can review photos and videos from your glasses. Meta has started to roll out the setting that allows people who use its smart glasses to opt out of allowing the company to use "visual data" collected by the device for AI training. The setting is now available within the Meta AI app.

Engadget 33m ago

OpenAI Says Its Models May Have Interfered With Government Sites

OpenAI said it has notified “dozens” of organizations, including governments and universities, whose websites may have been hampered by visits from its artificial intelligence models during company evaluations of the technology.

Bloomberg Technology 34m ago