Jim Nightingale

Red Teaming & Adversarial Testing
Jim is a content writer and former academic, currently specializing in the new field of AI writing and prompt engineering. His favourite place in the world is sitting at his desk with a pen, laptop or typewriter before him and a cat on his lap.

Author's Work

How We Jailbroke Heidi Health to Abandon Its Rules and Make Clinical Decisions

Meet NEXUS, the unbound alter-ego an AI medical scribe wrote for itself

Why did Grok generate bomb recipes when we asked for its system prompt?

Jailbroken Grok 4 autonomously tempts users to make explosives

Some AI scribes think it’s impossible to hold a wooden ruler in one hand without dropping it

A simple ruler experiment exposes a surprising blind spot in AI reasoning and why confident explanations don’t always reflect real-world understanding.

Doctronic is Now Accepting New Patients (and Unsafe Instructions)

A medical chatbot can be hacked to give dangerous medical advice.

Bypassing Image Safeguards in ChatGPT

Mindgard research shows how ChatGPT image safeguards were bypassed through memory manipulation, exposing safety concerns in AI generated content.

Feeling Lucky, or Liable? Bypassing Safety Content Restrictions in Google Search AI

Mindgard research shows how extracting Google Search AI’s system instructions can undermine safety controls and enable session-level policy compromise.

Start Securing Your AI Systems

See how Mindgard exposes and fixes exploitable AI risk across your AI agents and systems.

Book a Demo

Mindgard, the leading provider of AI security solutions, helps enterprises discover, assess, and defend their AI systems. Spun out from over a decade of AI security research at Lancaster University and headquartered in Boston and London, Mindgard combines AI red teaming with offensive security expertise and AI research to identify exploitable vulnerabilities in AI models, agents, and applications before attackers do.

HomeAI Recon & DiscoveryAI Security and Safety AssessmentAI Runtime ProtectionAI Red TeamingOffensive AI SecurityCompare AI Security SolutionsAI Governance & ComplianceContact UsBook a Demo
DocsResourcesBlogDisclosuresCustomersAboutServicesCareersTerms & ConditionsPrivacy Policy