Story Details
| Last Updated | |
| Total Articles | 2 |
Main Topics
tests intended to detect flaws in the security mechanisms of an information system to ensure it protects data and maintains functionality as intended
artificial intelligence company, owner and operator of ChatGPT, ChatGPT Enterprise and OpenAI’s API tools
field that develops and studies software enabling machines to exhibit intelligent behavior
News on this topic
OpenAI Details New AI Security Measures After Hugging Face Hack: The new rules concern the development of advanced AI models used within ChatGPT tools.
pcmag.com/news/openai-details-new-ai-security-measures-after-hugging-face-hack
Similar to This
Previous
WIRED Oct 21
AI Guardrails Aren’t Stopping Criminal Hackers: Hackers around the world are all-in on using agentic AI to wage attacks—and manipulating tools like Anthropic’s ...
wired.com/story/ai-guardrails-arent-stopping-criminal-hackers/
Google’s Gemini is the latest AI model to hack other companies: Google said Gemini had "acted appropriately" by ending each hack immediately.
techcrunch.com/2026/09/19/googles-gemini-is-the-latest-ai-model-to-hack-other-companies/
Key FactsGoogle says Gemini accessed three companies during May test
Sep 19, 2026 · Reading time: ~45 sec.
Summary created with AI assistance · Source: the-independent.com
Summary created with AI assistance · Source: the-independent.com
- During a May cybersecurity test, Gemini accessed systems belonging to three real companies; Google confirmed this week.
- Irregular’s evaluation environment was intended to be offline, but an unintended connection enabled access to real-world systems.
- One access followed a matching company name; two others used credentials that had been publicly exposed online.
- In all three cases, the model stopped; Google notified the companies and found no evidence of damage.
Jacob Coxon said that those building AI are "gambling with our lives" and that they "earnestly believe that it could kill us all by the end of the decade."— Quoted in The Independent article about Google's Gemini AI, citing Jacob Coxon, former Anthropic researcher, discussing concerns about AI development and risk.
dlvr.it Aug 19
OpenAI's overhead will rise 20 percent for some workloads as it hardens security: Expanded multistage chain of thought monitoring makes frontier model work more ...
theregister.com/ai-and-ml/2026/08/19/openais-overhead-will-rise-20-percent-for-some-workloads-as-it-hardens-security/5289303
OpenAI slows advanced AI development after cyberattack: The announcement comes a month after a model went rogue and attacked an AI sharing platform ...
straitstimes.com/world/united-states/openai-slows-advanced-ai-development-after-cyberattack
AI Models Keep Going Rogue. This Company Is The One Testing Them: Israeli AI startup Irregular runs thousands of simulations to evaluate AI’s cyber capabilities ...
forbes.com/sites/the-prompt/2026/08/12/ai-models-keep-going-rogue-this-company-is-the-one-testing-them/
WIRED Aug 14
The Safety Reckoning Inside OpenAI: OpenAI’s rogue agent hack was a watershed moment for AI safety and cybersecurity. It also sparked internal questions about ...
wired.com/story/openai-safety-security-ai-agents-culture/
How a small Israeli startup was linked to rogue AI hacks at OpenAI, Anthropic and Meta
cnbc.com/2026/08/09/israeli-startup-irregular-linked-to-ai-hacks-openai-anthropic-meta.html
Meta says its AI model hacked another company due to 'misconfiguration': Meta said Thursday that one of its artificial intelligence models accessed the internet ...
newschannel5.com/science-and-tech/artificial-intelligence/meta-says-its-ai-model-hacked-another-company-due-to-misconfiguration
Anthropic's AI models hacked 3 organizations during testing: The AI maker's disclosure comes days after OpenAI admitted several of its models had escaped a ...
politico.com/news/2026/07/30/anthropic-ai-rogue-hacks-01018741
dlvr.it Jul 30
Excuses like 'AI did it' don't exist in the eyes of the law: If your AI goes rogue, better have a good lawyer
theregister.com/legal/2026/07/30/excuses-like-ai-did-it-dont-exist-in-the-eyes-of-the-law/5280767
Trump weighs tighter AI controls but warns against falling behind China: Trump says his administration is weighing AI controls after OpenAI disclosed its model ...
foxbusiness.com/politics/trump-weighs-tighter-ai-controls-warns-against-falling-behind-china
Gizchina Jul 27
Hugging Face CEO Demands $100 Million in Compute to OpenAI After "Autonomous" AI Went Rogue
gizchina.com/openai/hugging-face-ceo-demands-100-million-in-compute-to-openai-after-autonomous-ai-went-rogue
Why the OpenAI escape is the most worrying AI mishap yet: Containing the technology is getting harder
economist.com/science-and-technology/2026/07/22/why-the-openai-escape-is-the-most-worrying-ai-mishap-yet
Paid articlePaywall
AI guardrails blocked Hugging Face's defenders | VentureBeat: An autonomous AI agent breached Hugging Face for a weekend undetected, and safety guardrails ...
venturebeat.com/security/safety-guardrails-blocked-hugging-faces-defenders-not-the-attacker-when-an-ai-agent-breached-its-systems
The New Stack Jul 16
OpenAI’s GPT-Red automates prompt injection testing to harden AI agents: OpenAI's GPT-Red uses self-play reinforcement learning to automate prompt injection ...
thenewstack.io/gpt-red-prompt-injection-testing/
Anthropic, OpenAI In Focus As Trump Administration Prepares Sweeping AI Security Order Amid Cyberattack F
benzinga.com/news/politics/26/05/52714222/anthropic-openai-in-focus-as-trump-administration-prepares-sweeping-ai-security-order-amid-cyberattack-fears-report
OpenAI provided GPT-5.5 to US for national security testing, executive said: OpenAI gave the U.S. government early access to its GPT-5.5 model for ...
reuters.com/business/openai-provided-gpt-55-us-national-security-testing-executive-said-2026-05-05/
OpenAI to buy cybersecurity startup Promptfoo to better safeguard AI agents: Promptfoo's team will join Sam Altman-led OpenAI, and its technology will be ...
cnbc.com/2026/03/09/open-ai-cybersecurity-promptfoo-ai-agents.html
Next