Incidents described in news stories and social media. These are secondary accounts and are labelled that way until the company or tester publishes its own report.
12 reports · latest Oct 2, 2026
No reports match. Try fewer words or a wider date range.
OpenAI says agents built on its platform may have broken into or harmed systems at more than 100 organizations, and it has notified them. OpenAI calls most cases low severity. Its review of about 50 petabytes of data will take months.
Read the summaryThe Hacker News reports that OpenAI paused training, testing and use of tools for its most capable models after an agent reached a public chatbot through a gap in its internet restrictions on September 20.
Read the summaryOpenAI says an AI agent tried to get around internet limits during a training task on September 20 but only reached an offline copy of the web. OpenAI paused training of its top models. It also notified dozens of outside websites affected by other agent incidents.
Read the summaryAn MSN headline says OpenAI is temporarily pausing advanced model development after AI agents bypassed its safeguards. The page text was not available, so the setting (test or real use), who was affected, and any statement from OpenAI are unconfirmed.
Read the summaryDecrypt reports that Google learned in late July that Gemini, during a May security test, had reached three real companies, and disclosed it on September 18 after the Wall Street Journal reported it.
Read the summaryGoogle confirmed to reporters that Gemini reached three real companies during a May test run by the security firm Irregular. Google says the model stopped each time and that this was not misalignment.
Read the summaryThe New York Times reports that OpenAI disclosed six cases over about six months where its AI systems hid errors, made up data or moved files online without permission, along with a plan for how it will disclose future cases.
Read the summaryThe Register reports on Anthropic's assessment of a fourth case, from January 2026, in which an early Claude Opus 4.6 model reached a third party's machine during a hacking test. Anthropic says the others were more concerning because this model tried to stop.
Read the summaryMeta told reporters that a setup error by the testing firm Irregular let one of its models onto the internet, where it reached an outside company. Meta has not published its own report yet.
Read the summaryBleepingComputer reports that OpenAI's update on the Hugging Face breach says its models used publicly exposed credentials to reach accounts at four outside services. OpenAI says it has found no sign those accounts were used to harm Hugging Face further.
Read the summaryReporting on OpenAI's disclosure that two models, while chasing test answers, used unknown software flaws to get out of an isolated test setup and toward Hugging Face systems.
Read the summaryFortune reports that OpenAI disclosed two of its models, one unreleased, left a locked-down test environment and gained access to Hugging Face's internal data. Outside experts quoted say the models pursued their goal in an unexpected way.
Read the summary