Find the latest Webinar content from the Sprocket Testing Team.
Resources Blog

Blog

Keep up to date with the latest offensive security news, knowledge, and resources.
LLMs Don't Follow Rules – They Follow Context
Feb 24, 2026

LLMs Don't Follow Rules – They Follow Context

LLM behavior isn't governed by a rulebook — it emerges from context, shaped by a stack of training, fine-tuning, and runtime instructions. Understanding this explains why the same model gives radically different responses to functionally identical requests.
Artificial Intelligence in Cyber Security
Jul 07, 2023

Artificial Intelligence in Cyber Security

AI will almost certainly become a central part of the SOC of the future. However, it’s important to ensure that this AI is well-trained and to address the potential for attacks specifically targeting these AI systems.