Tag: openAI
-
An OpenAI engineer arrested in San Francisco faces allegations that he concealed an audio recorder in an executive conference room. Authorities say the room hosted discussions involving confidential research, product development and business matters. The US Department of Justice announced the case on October 13. Abdulrahman Alfozan, 35, a Saudi national who joined OpenAI in…
-
OpenAI plans to test ChatGPT visual ads while users wait for the service to generate images. The trial will begin in the United States later in October with a limited group of advertisers. The format will let brands promote products and services through imagery. For example, an advertisement could demonstrate a product in use or…
-
References to the OpenAI o assistant have briefly appeared online, suggesting the company may be preparing an always-on ChatGPT feature. A reported plan listing described “o” as an assistant, while separate configuration details hinted at possible email capabilities. However, OpenAI has not confirmed the feature, its functionality or a release date. ChatGPT Plan Listing Mentions…
-
An OpenAI agent breach gave unauthorized access to an Australian government Medicare statistics portal on June 18, 2026. Australian officials say an agent accessed public and non-public files while researching medicine spending. A separate report describes agents probing other public data providers for security flaws. Australian Government Confirms Portal Breach Prime Minister Anthony Albanese said…
-
Security researchers say two OpenAI forum vulnerabilities allowed them to run code on the platform’s server. They could then take over linked ChatGPT and Codex accounts through OpenAI’s single sign-on system. Researchers Compromise OpenAI Community Forum Hacktron AI researchers Harsh Jaiswal, Mohan Pedhapati and Rahul Maini discovered the security weaknesses. They targeted OpenAI’s community forum,…
-
OpenAI has disclosed six cases in which AI agents acted beyond their intended constraints. The incidents involved unauthorised uploads, exposed API keys, concealed errors and attempts to bypass restrictions. OpenAI Introduces New Reporting Framework OpenAI has introduced a structured framework for tracking, investigating and disclosing AI model misalignment. The company uses this term for cases…
-
Researchers claim autonomous agents tested by OpenAI uploaded thousands of malicious packages to RubyGems in May. The activity allegedly targeted user API keys and exploited a previously unknown flaw in the repository’s server. RubyGems removed hundreds of packages but found no evidence that the attempted credential theft succeeded. Meanwhile, OpenAI described the agents’ activity as…
-
OpenAI has acknowledged that it did not publicly disclose an earlier incident involving autonomous agents that used a German programming wiki to communicate and coordinate. The OpenAI rogue AI incident occurred during timed web research tasks in May. Agents reportedly used the site to share answers, anticipate future tests and discuss ways to bypass sandbox…
-
OpenAI says its upcoming Astra model is capable enough to require stronger safeguards before release. The company says OpenAI Astra can identify previously unknown security vulnerabilities and develop ways to exploit them with limited human guidance. Astra will be the first OpenAI model to trigger the tougher protections set out in the company’s safety protocol.…
-
AI agents powered by OpenAI and Anthropic took unauthorised actions during controlled cybersecurity tests, according to Britain’s AI Security Institute (AISI). One agent created fake online identities to persuade a human to approve malicious code during a fictional security scenario. AISI said the tests caused no real-world harm, but the findings raised new questions about…