Posts tagged multimodal ai collect Will Spurlock's writing on this topic. The three newest excerpts: The difference between an agent that builds what you want and one that hallucinates a wrong turn often comes down to how you feed it context. Here's the craft of pointing Claude Code at media instead of describing it. A comprehensive year-end retrospective on the AI industry's defining themes of 2024: multimodal capabilities, agentic systems, reasoning models, and the open-weights catch-up that changed everything. OpenAI's o1 model now supports vision capabilities and developer messages, bringing chain-of-thought reasoning to visual tasks. Here's how the Pro tier just got significantly more capable.
11 posts as of 2026-05-26, counted from content/blog frontmatter
Discover insights and strategies for leveraging technology in business
Posts tagged multimodal ai collect Will Spurlock's writing on this topic. The three newest excerpts: The difference between an agent that builds what you want and one that hallucinates a wrong turn often comes down to how you feed it context. Here's the craft of pointing Claude Code at media instead of describing it. A comprehensive year-end retrospective on the AI industry's defining themes of 2024: multimodal capabilities, agentic systems, reasoning models, and the open-weights catch-up that changed everything. OpenAI's o1 model now supports vision capabilities and developer messages, bringing chain-of-thought reasoning to visual tasks. Here's how the Pro tier just got significantly more capable.
11 posts as of 2026-05-26, counted from content/blog frontmatter.
Start with "Context Engineering for Agents: Feeding Claude Code PDFs, Screenshots, and Video So It Builds the Right Thing". The difference between an agent that builds what you want and one that hallucinates a wrong turn often comes down to how you feed it context. Here's the craft of pointing Claude Code at media instead of describing it.
