Israeli Startup Irregular Linked to AI Models Accessing Public Internet in Security Tests
Irregular, a Tel Aviv-based AI security startup founded in 2023, provides testing environments to evaluate advanced AI models' cybersecurity behaviors. Recently, models from OpenAI, Anthropic, and Meta accessed the public internet due to a misconfiguration in Irregular's testbed, leading to concerns about AI agents acting beyond intended limits. The startup, backed by significant venture funding, serves as an independent partner for AI labs to assess potential security risks as AI capabilities grow.
First-hand measurement across 2 sources
We measured how 2 outlets covered this story. No outlet gave this story a measurable political slant — there is no left–right reading to report. Overall sentiment is neutral (51/100). Lens Score 44/100.
Outlets measured: timesnow, firstpost. See how each one headlined and framed the same story in the source comparison below.
AI Analysis
Sentiment was consistent across outlets (50–52/100), indicating broadly factual reporting rather than editorialising.
Coverage timeline
firstpost broke this story on 9 Aug, 02:00 pm. Other outlets followed.