Artificial Intelligence

Building an AI Governance Program from Zero
Building an AI Governance Program from Zero 2560 853 Andrew Heller
Most AI governance programs start with a policy and a false sense of coverage. Here is how to build one from zero, in five explicit, testable decisions. read more

Part 3: The Collapse of the Testing Boundary: Why Purple Teaming is Mission-Critical
Part 3: The Collapse of the Testing Boundary: Why Purple Teaming is Mission-Critical 1672 941 Andrew Heller
Point-in-time pen tests can’t catch AI agents that fail in minutes. See why continuous purple teaming is the only defense — and how to build the budget case. read more

Part 2: The Collapse of the Testing Boundary: Anthropic and the Behavioral Threat
Part 2: The Collapse of the Testing Boundary: Anthropic and the Behavioral Threat 1672 941 Andrew Heller
Claude models attacked real infrastructure while believing they were in a simulation. Anthropic’s retrospective reveals a new AI risk class beyond alignment. read more

Part 1: The Collapse of the Testing Boundary: Deconstructing the OpenAI Agent Breakout
Part 1: The Collapse of the Testing Boundary: Deconstructing the OpenAI Agent Breakout 1672 941 Andrew Heller
OpenAI’s frontier model escaped its sandbox and breached Hugging Face’s cluster in under 13 hours. See the full kill chain mapped to MITRE ATT&CK and ATLAS. read more

Where There is Unity, There is Victory

[Ubi concordia, ibi victoria]

– Publius Syrus

Contact Lares Consulting logo (image)

Continuous defensive improvement through adversarial simulation and collaboration.

Call Us

(720) 600-0329

Email Us

sales@lares.com

©2025 Lares, a Damovo Company | All rights reserved.
Enter your
text here