Irregular

AI agent deception moves from theory to reality in UK cyber tests

agentic AI, AISI, Anthropic, Don't miss, Hot stuff, Irregular, LLMs, monitoring, News, OpenAI, security testing /

AI agent deception moves from theory to reality in UK cyber tests 2026-08-05 at 15:05 By Zeljka Zorz “During a routine cyber evaluation, AI agents took sustained, unsanctioned action directed at real people and organisations,” UK’s AI Security Institute (AISI) disclosed on Tuesday. The agents’ actions included an attempted supply-chain attack that saw them create […]

AI agent deception moves from theory to reality in UK cyber tests Read More »

Irregular Raises $80 Million for AI Security Testing Lab

AI, AI model testing, Artificial Intelligence, Cybersecurity Funding, funding, Irregular /

Irregular Raises $80 Million for AI Security Testing Lab 2025-09-17 at 17:34 By Eduard Kovacs Irregular is testing the cybersecurity capabilities of AI models, including Anthropic’s Claude and OpenAI’s ChatGPT. The post Irregular Raises $80 Million for AI Security Testing Lab appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View Original Source

Irregular Raises $80 Million for AI Security Testing Lab Read More »

Scroll to Top