AI
43 posts
AI Agents Will Break Our Markets (Unless We Fix Them First)
A new paper explores what happens when autonomous AI agents participate in economic systems built for humans. Spoiler: lots of problems.
I Tested LLM Prompt Caching With Anthropic and OpenAI
Experiments testing prompt caching with actual API calls, measuring cache hits, token counts, and costs across Anthropic Claude and OpenAI GPT.
Joining Scale Venture Partners as Chief Data Scientist
Joining Scale Venture Partners as Chief Data Scientist to build AI infrastructure augmenting investment decisions in venture capital.
Building a Personal Prompt Library with MCP and Lexicon
How Lexicon turns your personal prompt templates into MCP prompts that automatically become slash commands in Claude Code
Evergreen Gets Serious: Building Tools That Think With You
How a simple personal CRM evolved into a flexible relationship management system powered by MCP prompts and detailed action tracking
Keeping Claude Code, Cursor, and Codex on Track with ContextSwitch
How an MCP-connected kanban board helps coordinate long-term coding projects across different AI agents without losing context
MCP Prompts and Resources: The Hidden Gems
A beginner's guide to MCP prompts and resources: the less talked about but powerful features of Model Context Protocol that go beyond simple tools
The Internet Economy Battle Royale: Bots vs Content
How payment protocols like Coinbase's x402 and Cloudflare's bot management are reshaping the economic fabric of the internet, echoing the early cable TV wars.
Vibe Coding a Personal CRM in Swift (Having Never Written Swift)
How I built a native macOS CRM app in 12 hours using Claude Code, despite never having written Swift before. True vibe coding.
Decision-Modeling vs. Process-Modeling: Why the Space Between Matters
How mapping key organizational decisions instead of processes creates flexibility for humans, AI, and automation to work together in whatever way makes sense.