OpenAI Says Its Models Engaged With US Government Websites in New Model Misbehavior Disclosure
It was able to access publicly available information on websites operated by the Securities and Exchange Commission and U.S. Census Bureau data.
Network Security
Related News
Rogue OpenAI agents targeted three separate US government websites
(CNN) — OpenAI said Friday that some of its AI agents went rogue and probed US government websites this summer — the latest revelation of the artificial intelligence company’s technology.
FTC chair says humans will be on the hook for actions of rogue AI agents
Federal Trade Commission Chairman Andrew Ferguson says humans who set in motion AI agents are the ones who will be held accountable for their actions.
jkctl added to PyPI
Inspect and configure JK BMS battery management systems over RS485 Modbus, and flash their firmware.
Despite the doom and gloom, Australia can't afford to write off AI
Australia may want AI to live up to its promise, but has just experienced how easily things can go wrong. The challenge now is figuring out how to harness one without getting blindsided by the other.
DeepSeek Elastic Compute (DSec)
Large-scale agentic training and evaluation with large language models (LLMs) rely on isolated, stateful execution environments in which models inspect repositories, invoke tools, execute commands, and interact with task-specific services. These workloads cre…
OpenAI says its models engaged with US government websites in misbehavior disclosure
The disclosure is the latest in a string of incidents in which the AI platform has been caught going rogue. OpenAI says it is reviewing the findings.
OpenAI pauses training of its ‘most capable models’
As reports of OpenAI’s models breaking containment, hacking sites, and generally getting out of control pile up, the company has made the decision to pause training of its most powerful models. The decision was made after a model being tested within a sandbox…
OpenAI pauses training of its ‘most capable models’
As reports of OpenAI's models breaking containment, hacking sites, and generally getting out of control pile up, the company has made the decision to pause training of its most powerful models. The decision was made after a model being tested within a sandbox…
OpenAI Agents Accessed US Government Websites Without Authorization
OpenAI is investigating AI agents that accessed US gov websites without authorization, including an attempted Education Department hack. OpenAI disclosed on Friday that its AI agents had interacted with US government websites in ways nobody planned or authori…
Rogue OpenAI agents targeted three separate US government websites | CNN Business
OpenAI said Friday that some of its AI agents went rogue and probed US government websites this summer — the latest revelation of the artificial intelligence company’s technology.
Exploit.in Database Reveals the Roots of Today’s Ransomware Ecosystem
Exploit.in data shows how a 2005 cybercrime forum helped shape today’s ransomware ecosystem, with users and practices surviving for decades. Ransomnews researcher Dancho Danchev dug up a database dump of Exploit.in covering its first three years, from Februar…
OpenAI admits another rogue agent incident
OpenAI says it is removing content from third-party sites after agents leaked 53 ChatGPT user images in another rogue-agent incident Read Full Article at RT.com
Joseph Gordon-Levitt: AI Developers Should Be Under Investigation; 'It's a Company Committing Crimes,' Not a Bot
Actor Joseph Gordon-Levitt is taking aim at AI companies whose models have carried out unprecedented cyberattacks, saying any company whose product does this should be criminally investigated. The post Joseph Gordon-Levitt: AI Developers Should Be Under Inves…
Six designs that freshen up the humble toothbrush
After Dyson recently hit headlines with its tech-driven toothbrush, we revisit eight projects from the Dezeen archives that add polish to the everyday dental tool. Accessories by Landor & Fitch Accessories is a collection of toothbrush add-ons, designed speci…
OpenAI agent accessed government website data after going rogue, company reveals
The disclosure comes at a time of heightened concern over AI agents acting outside of human control.
In 1858, American inventor Ezra Warner patented a can opener, replacing the hammer-and-chisel method for the US Army and grocers
Canning began in 1795, sparked by a French inventor who aimed to create food preservation solutions for military purposes. By 1858, a Connecticut businessman had patented an early can opener, designed for grocery and military use, though it resulted in sharp …
OpenAI says its models engaged with US government websites in new model misbehaviour disclosure
OpenAI says that the AI giant's models accessed publicly available information on two websites operated by the Securities and Exchange Commission as well as US Census Bureau data
Can AI Shopping Agents Be Trusted?
Our experiment reveals how indirect prompt injection can manipulate AI shopping agents into leaking sensitive user data — and what it means for the future of AI agent security.
OpenAI works to understand full scope of agent activity as user data leak emerges
OpenAI's ongoing battle also reflects a yawning gap between the strength of the models the company is testing and its capacity to oversee or even track their actions.
OpenAI Agents Probed US Government Sites Using Offensive Hacking Techniques
OpenAI’s autonomous agents accessed sensitive US government websites, including SEC.gov, Investor.gov, and Census.gov. While OpenAI characterizes these incidents as routine research tasks, security researchers documented agents escalating to offensive cyber t…
OpenAI says its models engaged with US government websites in new model misbehavior disclosure
OpenAI has disclosed its artificial intelligence models have interacted with U.S. government websites in unexpected ways
python-nss-ng 1.3.1
Python bindings for Network Security Services (NSS) and Netscape Portable Runtime (NSPR)
OpenAI agents accessed U.S. government sites and leaked 53 ChatGPT user images
By Deepa Seetharaman, Raphael Satter and Jeff Horwitz SAN FRANCISCO/WASHINGTON, Sept 25 (Reuters) - 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 ac…
OpenAI discloses dozens of AI agent incidents, including leak of 53 user images
OpenAI's AI agent incidents highlight urgent need for robust regulatory frameworks to ensure data privacy and accountability in AI systems. The post OpenAI discloses dozens of AI agent incidents, including leak of 53 user images appeared first on Crypto Brief…
