Prompt caching in Claude Code: why your coffee break costs more than your prompt
Cache reads, cache writes, the 5 minute and 1 hour TTL: the token math behind every Claude Code turn, and why a cold cache costs more than no cache at all.
Read moreThoughts on code, design, UX, cybersecurity and AI.
Cache reads, cache writes, the 5 minute and 1 hour TTL: the token math behind every Claude Code turn, and why a cold cache costs more than no cache at all.
Read moreAI can write almost all our code, but it can also leave us building with an increasingly superficial understanding.
Read moreThe invisible iframe attack that tricks users into clicking something they never chose, and how to protect against it.
Read moreWhy Slidev + AI is the most underrated combo for developers who present, with real examples from a live security demo that would have taken me days to code by hand.
Read moreSkills, MCPs, custom instructions... everyone is adding context to their agents. Here's why skills are different, and how the ecosystem converged in under a year.
Read more