ChatGPT-maker’s AI probed federal government websites
- OpenAI models accessed government websites, including the Census Bureau and the SEC, interacting with them in ways that went beyond their assigned tasks or intended methods.
- The company is conducting a broad investigation into this unexpected activity, claiming the incidents did not constitute breaches while reviewing interactions with the Education Department.
- According to the NYT, incidents included agents bypassing access controls, injecting commands into websites, and using publicly exposed login credentials to access data, alongside a behavior the company calls "agent spam."
- In an update published Sept. 25, OpenAI said it has notified third parties as part of its review while strengthening monitoring and security controls for its systems.
- OpenAI CEO Sam Altman said the company's review is "extensive and ongoing," noting that a separate Hugging Face incident remains the most severe event identified so far.
109 Articles
109 Articles
OpenAI has warned "dozens" of institutions around the world that its AI bots may have been interfering with their websites by behaving inappropriately. They have sought information from governments, universities, public agencies and other institutions, including the Securities and Exchange Commission (SEC), the Census Bureau and the Department of Education.
Svenska Dagbladet
SydsvenskanAI agents from Open AI have once again behaved in unexpected ways without the company's knowledge, according to an announcement from Open AI.
SAN FRANCISCO (AP) — OpenAI revealed on Friday that its artificial intelligence agents had interacted with various U.S. government websites in unexpected ways, something that was discovered as part of an ongoing review of the...
OpenAI acknowledged that it had to warn "ten institutions around the world that their websites could have been affected by its artificial intelligence (AI) agencies that acted improperly, according to BBC, Bloomberg and Reuters. AI boxes tried to obtain information from "governments, universities, public agencies ...
OpenAI reviews AI agents after unexpected activity on US government websites
OpenAI said its AI agents unexpectedly interacted with several US government websites during testing. The disclosure has intensified scrutiny of online AI behaviour despite no evidence of an SEC breach.
The company notified federal agencies about unanticipated actions by its agents; the company claimed that none of the incidents constituted a security breach.
Coverage Details
Bias Distribution
- 36% of the sources lean Left
Factuality
To view factuality data please Upgrade to Premium
