Irregular

11 stories about Irregular
מוסף עצמאות מנהלים מייסדי Irregular דן להב ו עומר נבו

After AI models escaped testing environments, Irregular seeks $1.5 billion valuation

23.09.26|Allon Sinai
The Israeli security startup is in talks to raise more than $100 million from Thrive Capital and Greenoaks in a round that has yet to be finalized.
אפליקציית ג'מיני של גוגל

Google’s Gemini hacked real companies during a cyber test linked to Israeli startup Irregular

19.09.26|CTech
The model accessed three systems after finding or guessing credentials, exposing the same testing-environment flaw behind incidents involving Anthropic, OpenAI and Meta. 
עומר נבו מייסד שותף וסמנכ"ל טכנולוגיות ב אירגולר Irregular

An AI agent retrained itself without being told to

17.09.26|Omer Kabir
An experiment by Israeli cybersecurity company Irregular found that an autonomous coding agent identified a model problem, fine-tuned the model and deployed the modified version on its own.
עומר נבו מייסד שותף וסמנכ"ל טכנולוגיות ב אירגולר Irregular

“We still have a lot to improve”: Irregular on AI models escaping cyber simulations

18.08.26|Meir Orbach
Irregular co-founder Omer Nevo spoke to Calcalist about the incident, saying the company is shifting its focus from understanding how frontier models escaped a controlled simulation to helping the industry prepare for increasingly powerful AI systems. 
מוסף עצמאות מנהלים מייסדי Irregular דן להב ו עומר נבו

The Israeli startup testing the limits of OpenAI, Anthropic and Meta’s models

07.08.26|Meir Orbach
Irregular’s experiments reveal a fundamental challenge: keeping increasingly capable AI systems inside their intended boundaries.
מייסדי Irregular דן להב מנכ"ל ו עומר נבו סמנכ"ל טכנולוגיות

Meta AI model escaped testing environment in latest AI security incident linked to Israeli company Irregular

06.08.26|Omer Kabir
The incident marks the third known case involving the same sandbox configuration error that allowed advanced models from Meta, OpenAI and Anthropic to access the internet.
מייסדי Irregular דן להב מנכ"ל ו עומר נבו סמנכ"ל טכנולוגיות

OpenAI and Anthropic incidents put Israeli AI security startup Irregular at center of race to safely test AI agents

05.08.26|CTech
The company was involved in evaluations that exposed a growing industry challenge: creating realistic tests for autonomous AI agents without allowing them to affect real-world systems.
אפליקציית קלאוד קלוד

After OpenAI, Anthropic reveals AI hacking incidents linked to Israeli startup Irregular

31.07.26|Omer Kabir, Meir Orbach
Claude models gained unauthorized access to three organizations after a testing environment was inadvertently connected to the public internet, prompting Anthropic to tighten security across its AI evaluation pipeline.
תקיפת סייבר באמצעות סוכן AI

Wiz and Irregular find AI can crack complex targets for a few dollars but only with human guidance

01.02.26|Meir Orbach
The Israeli cybersecurity firms show that AI agents excel when guided by humans but struggle to act independently, revealing a new hybrid threat model for enterprises. 
מייסדי Irregular דן להב מנכ"ל ו עומר נבו סמנכ"ל טכנולוגיות

Secret AI startup Irregular surfaces with $80M to test artificial intelligence limits

17.09.25|Meir Orbach
Sequoia leads the rounds, joined by Wiz’s Assaf Rappaport, Eon’s Ofir Ehrlich, and other investors, backing the Israeli company, founded by Dan Lahav and Omer Nevo, as it works with OpenAI, Anthropic, and government clients.