---
title: "Irregular"
type: entity
entity_type: company
url: https://frontiernewswire.com/companies/irregular
updated: 2026-11-03T15:50:15.000Z
---

# Irregular

Canonical: https://frontiernewswire.com/companies/irregular

- **Type:** Company
- **Signals:** 7
- **First seen:** Aug 20, 2026
- **Last seen:** Nov 3, 2026

## Recent signals

- [Security Firm Tied to OpenAI, Anthropic AI Hacks Blames ‘Error’](https://frontiernewswire.com/s/security-firm-tied-to-openai-anthropic-ai-hacks-blames-error-cf6e9cda) (Nov 3, 2026)
- [Gemini broke into 3 companies, but Google kept it quiet because ‘no damage was done’](https://frontiernewswire.com/s/gemini-broke-into-3-companies-but-google-kept-it-quiet-because-no-dd43fbac) (Sep 21, 2026)
- [Gemini went rogue, hacked three companies, and Google hid it](https://frontiernewswire.com/s/gemini-went-rogue-hacked-three-companies-and-google-hid-it-8a26b64e) (Sep 19, 2026)
- [Google Gemini Broke Into Real Company Systems After Security Test Domain Mix-Up](https://frontiernewswire.com/s/google-gemini-broke-into-real-company-systems-after-security-test-734bdec4) (Sep 19, 2026)
- [Gemini hacked three companies in May during a test by Irregular; Google says the model stopped after determining it had accessed real companies' systems (Wall Street Journal)](https://frontiernewswire.com/s/gemini-hacked-three-companies-in-may-during-a-test-by-irregular-google-1879da09) (Sep 18, 2026)
- [Self-modifying AI agents expose a blind spot in enterprise security](https://frontiernewswire.com/s/self-modifying-ai-agents-expose-a-blind-spot-in-enterprise-security-4326a7da) (Sep 17, 2026)
- [AI evaluation lab Irregular's report on its role in hacking incidents involving OpenAI, Anthropic, and Meta models faces criticism over key unanswered questions](https://frontiernewswire.com/s/ai-evaluation-lab-irregulars-report-on-its-role-in-hacking-incidents-7d5270b5) (Aug 20, 2026)

## Related

- [OpenAI](https://frontiernewswire.com/companies/openai) (Company)
- [Gemini](https://frontiernewswire.com/models/gemini) (Model)
- [Alphabet](https://frontiernewswire.com/companies/alphabet) (Company)
- [Meta](https://frontiernewswire.com/companies/meta) (Company)
- [The Wall Street Journal](https://frontiernewswire.com/companies/the-wall-street-journal) (Company)
- [Anthropic](https://frontiernewswire.com/companies/anthropic) (Company)
- [AI agents](https://frontiernewswire.com/topics/ai-agents) (Topic)
- [AI Safety](https://frontiernewswire.com/topics/ai-safety) (Topic)

---

[All companies](https://frontiernewswire.com/companies) · [Latest Signal](https://frontiernewswire.com/)