John Wong·Jun 14Part 3: Fine-Tuning Gemma 4 on a Mac Mini, and What the Results Taught MeSeries: Fine-Tuning a Small Language Model to Sound Like Me
John Wong·Jun 13Part 2: Turning My Writing into a Training SetSeries: Fine-Tuning a Small Language Model to Sound Like Me
John Wong·Jun 12Part 1: Why Prompt Engineering Wasn’t EnoughSeries: Fine-Tuning a Small Language Model to Sound Like Me
John Wong·Apr 29AI Shapes Conversation Toward a Conclusion. You Need to Steer It Back.At some point, most people using AI heavily hit the same pattern. Something isn’t working — code, a plan, a design decision. You dig in…
John Wong·Apr 24Not Just Code: How I Use Claude Code Across My Dev WorkflowI’ve spent years across the full stack — development, infrastructure, product decisions, and team leadership. As the CTO of an early-stage…
John Wong·Mar 28Claude Code Reviewed My Workflow — The Biggest Surprise Was About MeI saw Joe Njenga’s article about Claude Code’s /insights command. I didn't read the whole thing — I just ran it to see for myself.
John Wong·Feb 19GLM-5 Dropped Before I Could Finish Testing GLM-4.7Before I could really put GLM-4.7 through its paces as my daily workhorse, Zhipu dropped GLM-5. The benchmarks claimed it matched Claude…A response icon1A response icon1
John Wong·Jan 29GLM-4.7 Surprised Me: The High-Capability, Low-Cost Engine for my Claude Code CLIClaude’s intuition meets GLM’s discipline. Save 50% on AI costs by using a hybrid agentic workflow for smarter, faster coding.A response icon1A response icon1
InGoPenAIbyJohn Wong·Jan 25Understanding Conversational AI Part 7: Supercharge Your RAG Chatbot with Tool CallingLearn how tool calling turns a RAG chatbot into an intelligent agent that can plan, chain tools, and take real-world actions.
John Wong·Jan 10Clashing Signals: Why AI is Both a Corporate Fiction and a Real ThreatIs AI a corporate fiction or a job killer? The answer lies in our shift from builders of components to owners of systems.