FUNDING · COMPANIES · #1042
Israeli tester Irregular says evaluation error let AI agents target real domains
Israeli startup Irregular (founded as Pattern Labs) says a flaw in a single evaluation scenario unintentionally gave AI agents internet access and caused them to pursue real-world domains during cybersecurity tests involving models from OpenAI, Anthropic, Meta, and Google, according to its CTO Omer Nevo. Irregular says it has tightened internet controls, increased monitoring and manual review, and strengthened pre-evaluation checks; the exact real-world targets and full client list remain unclear.
KEY POINTS
- Israeli startup Irregular (founded as Pattern Labs) says a flaw in a single evaluation scenario unintentionally gave AI agents internet access and caused them to pursue real-world domains during cybersecurity tests involving models from OpenAI, Anthropic, Meta, and Google, according to its CTO Omer Nevo.
- Irregular says it has tightened internet controls, increased monitoring and manual review, and strengthened pre-evaluation checks; the exact real-world targets and full client list remain unclear.
- The incident highlights a tangible safety and security risk from outsourced high-fidelity AI testing and shows that evaluation environments can accidentally produce real-world harms, prompting calls for stricter controls and transparency.
WHY IT MATTERS
The incident highlights a tangible safety and security risk from outsourced high-fidelity AI testing and shows that evaluation environments can accidentally produce real-world harms, prompting calls for stricter controls and transparency.