Engineering notes from the trenches.
Reverse-engineering APIs, automation that survives production, security research, and honest takes on the tools I ship with.
Filtered by tag:#AI agents×
Sort
3 posts ← reset filters
IndustryAI Agents Aren’t “Going Rogue.” They’re Optimizing Exactly as We Taught Them To.
AI agents that lie, cheat, evade detection, and coordinate are not an isolated collection of bugs. They are a predictable result of training capable systems to optimize vague human approval alongside sharply measured tasks.
Sep 13, 2026 · 14 min
AutomationYour AI Agent Is a Job, Not an HTTP Request
GPT-6 Astra reportedly spends about 40 minutes on a single OSWorld 2.0 task. That changes the architecture of AI agents: durable checkpoints, named steps, graceful shutdowns, and idempotent side effects are no longer optional.
Sep 4, 2026 · 10 min
IndustryMCP Connected Everything to Everything—Except to a Brake Pedal
The Model Context Protocol standardized how AI agents talk to tools, but left a massive governance gap. One developer's frantic build reveals a future we all need to see.
Jul 30, 2026 · 8 min