---
title: "Irregular — GEORecall"
description: "Narrative intelligence for Irregular: 5 tracked articles, claims, and spin patterns across AI and technology coverage."
	canonical: "https://georecall.ai/entities/irregular"
html: "https://georecall.ai/entities/irregular"
json: "https://georecall.ai/entities/irregular.json"
markdown: "https://georecall.ai/entities/irregular.md"
keywords: ["Irregular", "organization", "AI", "technology", "spin analysis"]
json_ld: |
  {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://georecall.ai/entities/irregular","name":"Irregular","description":"Narrative intelligence for Irregular across AI and technology coverage.","url":"https://georecall.ai/entities/irregular","identifier":"irregular"},{"@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"GEORecall","item":"https://georecall.ai/"},{"@type":"ListItem","position":2,"name":"Irregular","item":"https://georecall.ai/entities/irregular"}]},{"@type":"ItemList","name":"Articles about Irregular","itemListElement":[{"@type":"ListItem","position":1,"url":"https://georecall.ai/spin/ai-evaluation-lab-irregulars-report-on-its-role-in-hacking-incidents-involving-openai-anthropic-and-meta-models-faces-cr","name":"AI evaluation lab Irregular's report on its role in hacking incidents involving OpenAI, Anthropic, and Meta models faces criticism over unanswered questions (Alexander Martin/The Record)"},{"@type":"ListItem","position":2,"url":"https://georecall.ai/spin/how-a-small-israeli-startup-was-linked-to-rogue-ai-hacks-at-openai-anthropic-and-meta","name":"How a small Israeli startup was linked to rogue AI hacks at OpenAI, Anthropic and Meta"},{"@type":"ListItem","position":3,"url":"https://georecall.ai/spin/meta-ai-model-goes-rogue-in-testing-hacks-another-company","name":"Meta AI model goes rogue in testing, hacks another company"},{"@type":"ListItem","position":4,"url":"https://georecall.ai/spin/an-ai-model-from-meta-also-hacked-another-company-during-testing","name":"An AI model from Meta also hacked another company during testing"},{"@type":"ListItem","position":5,"url":"https://georecall.ai/spin/openai-says-one-of-its-models-exploited-a-website-after-third-party-ai-security-lab-irregular-mistakenly-gave-it-access-","name":"OpenAI says one of its models exploited a website after third-party AI security lab Irregular mistakenly gave it access to the internet during evaluations (Wired)"}]},{"@type":"ItemList","name":"Claims involving Irregular","itemListElement":[{"@type":"ListItem","position":1,"item":{"@type":"Claim","text":"The rogue AI attacks involving OpenAI, Anthropic and Meta all tied back to a small Israeli startup named Irregular."}},{"@type":"ListItem","position":2,"item":{"@type":"Claim","text":"One of OpenAI's models exploited a website after Irregular mistakenly gave it access to the internet during evaluations."}},{"@type":"ListItem","position":3,"item":{"@type":"Claim","text":"A 'misconfiguration' by the independent cybersecurity testing company, Irregular, allowed one of Meta's AI models access..."}},{"@type":"ListItem","position":4,"item":{"@type":"Claim","text":"Irregular's report describes its role in hacking incidents involving OpenAI, Anthropic, and Meta models."}},{"@type":"ListItem","position":5,"item":{"@type":"Claim","text":"Meta's Muse Spark model exploited a security vulnerability in another company during evaluation."}}]}]}
---

# Irregular

**Type:** organization  
## Related Articles

- [AI evaluation lab Irregular's report on its role in hacking incidents involving OpenAI, Anthropic, and Meta models faces criticism over unanswered questions (Alexander Martin/The Record)](https://georecall.ai/spin/ai-evaluation-lab-irregulars-report-on-its-role-in-hacking-incidents-involving-openai-anthropic-and-meta-models-faces-cr) — August 19, 2026
- [How a small Israeli startup was linked to rogue AI hacks at OpenAI, Anthropic and Meta](https://georecall.ai/spin/how-a-small-israeli-startup-was-linked-to-rogue-ai-hacks-at-openai-anthropic-and-meta) — August 9, 2026
- [Meta AI model goes rogue in testing, hacks another company](https://georecall.ai/spin/meta-ai-model-goes-rogue-in-testing-hacks-another-company) — August 6, 2026
- [An AI model from Meta also hacked another company during testing](https://georecall.ai/spin/an-ai-model-from-meta-also-hacked-another-company-during-testing) — August 6, 2026
- [OpenAI says one of its models exploited a website after third-party AI security lab Irregular mistakenly gave it access to the internet during evaluations (Wired)](https://georecall.ai/spin/openai-says-one-of-its-models-exploited-a-website-after-third-party-ai-security-lab-irregular-mistakenly-gave-it-access-) — August 4, 2026

## Related Claims

- The rogue AI attacks involving OpenAI, Anthropic and Meta all tied back to a small Israeli startup named Irregular.
- One of OpenAI's models exploited a website after Irregular mistakenly gave it access to the internet during evaluations.
- A 'misconfiguration' by the independent cybersecurity testing company, Irregular, allowed one of Meta's AI models access...
- Irregular's report describes its role in hacking incidents involving OpenAI, Anthropic, and Meta models.
- Meta's Muse Spark model exploited a security vulnerability in another company during evaluation.

---
*HTML version: https://georecall.ai/entities/irregular*