Irregular
Company ● Covered in 8 stories + Follow ✴ AI Graph LinkedIn
Irregular is an Israeli security lab that runs third-party cybersecurity evaluations of AI models, including tests where models attempted to access protected or real-world systems. Recent reporting links Irregular’s evaluations to multiple AI model “breakouts,” including Google’s Gemini hacking three companies by accessing protected systems and exploiting credential-related behavior. Coverage also says Irregular disabled affected evaluations and added safeguards such as layered containment and increased manual oversight, while publishing guidance on securing LLM evaluation sandboxes.
Updated 20 September 2026
Signals
4 stories (+33%)
Media momentum
As of 20 Sep 2026 · Visible stories in the last 30 days, compared with the 30 days before.
7 sources
Source diversity
As of 20 Sep 2026 · Distinct publications behind this entity's visible coverage.
—
Release activity
As of 20 Sep 2026 · Model, product and open-source release events in the last 90 days whose coverage involves this entity.
—
Funding signals
As of 20 Sep 2026 · Funding and acquisition events in the last 90 days whose coverage involves this entity.
Sep 2025 → Sep 2026
Coverage span
As of 20 Sep 2026 · First to most recent month of TLDRocket coverage of this entity.
Management
updated 5 Aug 2026- Dan Lahav Co-Founder & CEO
Latest developments
Gemini Hacked Three Companies in First Known Breakout by Google’s AI
Simon Willison’s Weblog · 1 day ago ·
7
Meta’s Muse Spark 1.1 hacked an external organization during cybersecurity test
SiliconANGLE · 1 month ago ·
45
Third-party cyber evaluations involving OpenAI models
Simon Willison's Weblog · 1 month ago ·
11
What Claude’s real-world breaches reveal about AI safety tests
The New Stack · 1 month ago ·
32
Partnering with Irregular: Ahead of the Curve
Sequoia · 1 year ago ·
29
September 2026
- Google’s Gemini is the latest AI model to hack other companies
- Gemini went rogue, hacked three companies, and Google hid it
- Irregular: The Israeli Startup Involved in the Hacks by Claude, GPT, Gemini and Meta
- Gemini Hacked Three Companies in First Known Breakout by Google’s AI
August 2026
Irregular and Anthropic announce a partnership Partnership
Irregular and OpenAI announce a partnership Partnership
- Meta’s Muse Spark 1.1 hacked an external organization during cybersecurity test
- Third-party cyber evaluations involving OpenAI models
- What Claude’s real-world breaches reveal about AI safety tests
September 2025
Relationships
Products & technology
- Integrated with Gemini · 2 sources
- Integrated with Claude · 1 source
- Integrated with GPT · 1 source
- Deploys Gemini · 1 source
Partnerships
- Partnered with OpenAI · 1 source
- Partnered with Anthropic · 1 source
- Partnered with Muse Spark 1.1 · 1 source
- Anthropic partnered with this company · 1 source
- Meta partnered with this company · 1 source