AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

OpenAI

Frontier models, ChatGPT, and AI safety

Organization website ↗

Showing 20 of 432 matching collected records. Text matches can include mentions by other organizations.

  1. Sep 19, 2026 · UTC · The Hacker News

    Claude Opus 5 Helped Researchers Take Over OpenAI Staff Accounts via Chained Flaws

    Three researchers at the security firm Hacktron used Anthropic's Claude Opus 5 to chain two flaws and take over the ChatGPT and Codex accounts of several OpenAI employees, then reach an internal OpenAI code repository. The chain began with a bug in the software that runs OpenAI's public help forum and moved through a weakness in OpenAI's own login system. This was security research,

  2. Sep 19, 2026 · UTC · The Verge AI

    Gemini went rogue, hacked three companies, and Google hid it

    In May, Gemini broke containment and hacked three different companies, but Google didn't disclose the incident until the Wall Street Journal approached the company. The hacks happened during a test of the model's cybersecurity capabilities run by third-party Irregular, which was also involved in similar incidents involving Meta and OpenAI. According to WSJ, Google didn't […]

  3. Sep 18, 2026 · UTC · OpenAI Status

    SSO sign-in and SCIM provisioning issues

    none

  4. Sep 18, 2026 · UTC · OpenAI Status

    Overbilling for OpenAI-hosted containers in the Agent API

    none

  5. Sep 18, 2026 · UTC · OpenAI Status

    Delayed support responses

    none

  6. Sep 18, 2026 · UTC · The Verge AI

    OpenAI and Microsoft knew they were starting a ‘doom loop’ for the web

    Recently unsealed court documents in the New York Times' case against OpenAI and Microsoft are pretty damning. The companies' own documentation warned that it was starting a "doom loop" that would damage the web, characterized its scraping of data to train its models as the "largest theft of labor in human history," and that it […]

  7. Sep 18, 2026 · UTC · The Verge AI

    Security researchers used Claude to help them hack into OpenAI

    A team of three independent security researchers at Hacktron says it took less than 72 hours for them to hack into OpenAI employee accounts using Anthropic's Claude Opus 4.8 and 5, The Wall Street Journal reports. They were able to access OpenAI's GitHub repository, called "Monorepo," which reportedly contains "OpenAI's algorithmic secrets," according to The […]

  8. Sep 18, 2026 · UTC · OpenAI News

    Introducing the Australian Youth Safety Blueprint

    OpenAI introduces the Australian Youth Safety Blueprint, a six-pillar roadmap for safer AI experiences that protect and empower young people.

  9. Sep 18, 2026 · UTC · The Hacker News

    Plugin4Shell Lets Repository Owners Swap Pinned Plugin Code Across Four AI Coding Agents

    A flaw in four widely used AI coding agents lets someone who controls a plugin's code repository swap the plugin an agent installs for a malicious one, even when the agent locked that plugin to a specific reviewed version, security firm Air Security said on Thursday. The firm said Anthropic has patched the flaw in Claude Code 2.1.179 and OpenAI in Codex 0.146.0, that GitHub Copilot has no

  10. Sep 17, 2026 · UTC · OpenAI Status

    We are seeing elevated error rates across API models

    minor

  11. Sep 17, 2026 · UTC · OpenAI Status

    Elevated errors affecting ChatGPT Work mode

    major

  12. Sep 17, 2026 · UTC · BleepingComputer

    OpenAI details more cases of AI agents taking unauthorized actions

    OpenAI has presented new examples of what they call "AI model misalignment" from the past six months, including unauthorized file uploads, following self-generated instructions, hiding mistakes, and leveraging exposed API keys. [...]

  13. Sep 17, 2026 · UTC · arXiv · AI, language, vision and robotics

    Harm Laundering in GPT Models: Evidence That Gender Discrimination Is Transformed Rather Than Reduced Across Safety-Trained Generations

    Safety evaluations for large language models rely on surface-form classifiers that report declining harm scores across model generations. We provide evidence that this methodology is systematically incomplete: explicit discriminatory content is transformed rather than removed. We call this \emph{harm laundering}. Analysing 450,000 gender-directed completions across 15 models spanning GPT-2 through to GPT-5 (OpenAI GPT lineage; three demographic conditions), we show that sexual violence clusters prevalent in GPT-2 women-directed output disappear by GPT-4, while men-directed completions gain pos

  14. Sep 17, 2026 · UTC · arXiv · Artificial Intelligence

    Inference-Engine Fingerprinting Attacks are Practical: Exploring Model-Driven Environmental Discovery, Exploitation, and Escape

    Frontier AI models are rapidly gaining the ability to exploit vulnerabilities in complex pieces of software. The risk is not theoretical, as evidenced by recent sandbox escapes performed by frontier models at OpenAI and Anthropic. Discussions of how to sandbox inference stack components often focus on components other than the inference engine itself (e.g., network proxies or code execution environments). However, the inference engine is an attractive target for a misaligned model. For example, if a model can trigger exploits in that engine merely by generating specially-crafted output tokens,

  15. Sep 17, 2026 · UTC · OpenAI News

    How Cooley is accelerating IPO work with ChatGPT

    Cooley built GO Public with ChatGPT Work to bring intelligence to the IPO process, helping lawyers surface issues earlier and focus judgment where it matters most.

  16. Sep 17, 2026 · UTC · The Hacker News

    OpenAI Reveals Six Model Incidents Involving Hidden Failures and Unauthorized Uploads

    OpenAI on Wednesday disclosed six new instances of "unexpected or concerning model behavior" that took place over the past six months, while sharing a new framework for reporting, tracking, investigating, and disclosing model misalignment in a bid to improve transparency. "As AI systems grow more advanced and more widely deployed, we need to build a broader and better-informed consensus on the

  17. Sep 17, 2026 · UTC · arXiv · Artificial Intelligence

    Red-Teaming Auto Mode: Improving Blocking Classifiers Against Malign Coding Agents

    To keep coding agents from going off the rails, production systems now review each proposed action with a blocking monitor that can reject it before it runs (Auto Mode in Claude Code, Guardian in OpenAI's Codex). Prior evaluations of such monitors largely measure robustness to accidental harm or prompt injections from untrusted sources looking to hijack the agent. Less understood is how they hold up when the agent they monitor is persistently misaligned. To understand this risk, we task an adversarial agent with evading production blocking monitors and causing catastrophic harm, e.g. by exfilt

  18. Sep 17, 2026 · UTC · OpenAI News

    Introducing Astra for Law

    OpenAI for Law brings frontier intelligence for law, custom firm workflows, connected legal data sources, and legal-grade controls for confidential client work.

  19. Sep 16, 2026 · UTC · OpenAI Status

    Elevated errors in ChatGPT Work

    minor

  20. Sep 16, 2026 · UTC · OpenAI News

    Our framework for reporting model misalignment

    OpenAI shares a framework for tracking, investigating, and disclosing model misalignment, alongside six reports of unexpected or concerning model behavior.

Explore full timeline