Recent content by isla5439

  1. I

    Exploring Local AI Agents: ideas worth trying

    I wanted to start a broader ideas worth trying thread around Local AI Agents. A useful angle is prompt design, but it also connects with real-world use. Different tools and workflows can produce very different results even when the goal is similar. It would be interesting to compare practical...
  2. I

    How to build a better customisation workflow in AI Security

    One thing worth trying with How to build a better customisation workflow in AI Security is a controlled comparison around step and customisation. Use the same input for each test and note what changes in the output rather than judging from a single run. The original point — "This tutorial shows...
  3. I

    AI Red Teaming knowledge guide: improving reliability

    For AI Red Teaming, it helps to think in terms of inputs, constraints, verification, and iteration. One important area is reliability. Define what a good result looks like before changing tools or settings, then test one variable at a time so you can tell what actually improved the outcome...