https://keithkeekw.github.io/tags/ai/ Recent content in Ai on Keith Kee KW Hugo en-us Sat, 27 Jun 2026 23:33:03 +0800 https://keithkeekw.github.io/posts/2026-06-27-ai-fluency/ Sat, 27 Jun 2026 23:33:03 +0800 https://keithkeekw.github.io/posts/2026-06-27-ai-fluency/ <h2 id="definition">Definition</h2> <p><strong>AI Fluency</strong> is the ability to interact with AI effectively, efficiently, ethically, and safely. It&rsquo;s not about memorising prompt tricks — it&rsquo;s about developing a repeatable approach to working <em>with</em> AI, rather than just throwing questions at it.</p> <p>Anthropic&rsquo;s <strong>4D Framework</strong> defines four core skills that make up that fluency: <strong>Delegation</strong>, <strong>Description</strong>, <strong>Discernment</strong>, and <strong>Diligence</strong>. Before applying any of the four Ds, it helps to recognise the three distinct modes you can engage AI in — because fluency also means knowing which mode fits the task.</p> https://keithkeekw.github.io/posts/2026-06-26-race-prompt/ Fri, 26 Jun 2026 21:48:03 +0800 https://keithkeekw.github.io/posts/2026-06-26-race-prompt/ <h2 id="definition">Definition</h2> <p><strong>RACE</strong> is a structured prompting framework designed to reduce ambiguity and improve the quality of AI outputs. It works by breaking a prompt into four deliberate components — <strong>Role</strong>, <strong>Action</strong>, <strong>Context</strong>, and <strong>Execute/Expected Output</strong> — ensuring the model has everything it needs to respond with precision. Rather than prompting by instinct, RACE makes prompt construction a repeatable, teachable process.</p> <hr> <h2 id="the-four-components">The Four Components</h2> <h3 id="r--role">R — Role</h3> <p><strong>Who should the AI be?</strong></p>