Welcome to katecarruthers.com

Disclaimer: The opinions expressed here are solely my own and not those of any employer, client, or affiliated organisation.

Sign in Subscribe

agentic ai

AI is getting smarter, but is it becoming intelligent?

AI is getting smarter, but is it becoming intelligent?

OpenAI’s Chief Scientist warns that we are building increasingly capable AI systems we cannot fully explain or reliably monitor. Yann LeCun argues that language fluency is not intelligence. Both may be right, and that is where the future gets interesting.

Prompt injection is not a bug you can patch

Prompt injection is not a bug you can patch

Prompt injection is not a bug that a better model can patch. If an AI agent is tricked, the real question is what it can access, change or send before anyone notices.

The skills we need in the AI age

The skills we need in the AI age

AI skills are more than better prompting. We need people who can use AI well, design agentic workflows, govern risk and build the technical capability Australia needs.

AI is changing the terms of cyber defence

AI is changing the terms of cyber defence

AI can help cyber defenders move faster, but speed is only useful if they can control the consequences. As AI systems gain the ability to act, the hard question is not just what they can do, but who gives them authority and who is accountable when something goes wrong.

image of a scary AI with screaming faces and a zombie like green creature standing in front of technology

How would you turn off your AI if it went rogue?

If an AI system starts behaving in ways you did not expect, who can actually stop it? Here's a practical guide to designing AI shutdown capability, from authority and access controls to safe fallbacks and a realistic kill-switch checklist.

image of essential 8 - source https://australiancybersecuritymagazine.com.au/asd-to-retire-essential-eight-within-two-years-consults-on-replacement/#prettyPhoto

The Essential Eight is not enough for AI-enabled cyber attacks

The Essential Eight is a vital protective baseline, but it is not enough to protect against AI-enabled cyber threats. Why organisations need stronger controls, assurance, resilience and recovery in the age of AI agents.

When the Test Becomes the Threat Model

When the Test Becomes the Threat Model

The OpenAI and Hugging Face incident shows why agentic AI governance cannot stop at the model. The real risk lies in the environment: tools, permissions, incentives, evidence and the ability to stop an agent before an evaluation becomes an incident.

© 2002-2026 Kate Carruthers | Carruthers Consulting Pty Ltd ABN 68682757268