Welcome to the world of Statecharts The world of statecharts describes what statecharts are, their benefits and drawbacks, how they differ from state machines, and practical examples on how to use them.
GoDaddy Gave a Domain to a Stranger Without Any Documentation What would you do if your organization had used a domain name for 27 years, and the registrar holding the domain seized it without any advance warning? All
EU Age Control: The trojan horse for digital IDs A technical look at the EU age verification reference app — the gap between marketed and shipped cryptography, relay attacks the protocol can't stop, and why the 'privacy-preserving' system is a trojan horse for digital ID infrastructure.
It's OK to Use Coding Assistance Tools To Revive The Projects You Never Were Going To Finish I tried to use Claude Code with Opus 4.6 to implement a connector between Youtube Music and opensubsonic. The end result was a fairly short amount of time to get a working project.
Making the Rails Default Job Queue Fiber-Based I tried Async::Job for my LLM apps, hit its limits, and patched Solid Queue to run jobs as fibers instead.
congrats on failing to launch; weirdfriends log 1 7 months, 221 commits, and I still haven’t told anyone to try my app. A reflection on what went wrong.
Context Is Finite. Who Maintains It? Context in LLM systems is finite. Today, developers maintain it. What happens if the agent learns from its work and takes on part of that responsibility?
Naming Things Is Easy Now “There are only two hard things in Computer Science: cache invalidation and naming things.” - Phil Karlton I don't think naming things is hard anymore (cache invalidation is about the same)....
GPT-5.5 is a biased evaluator: authorship and order effects - Guillaume Valmont's Weblog While comparing medium, high, and extra-high reasoning modes on the same task, I uncovered consistent authorship and presentation-order effects in GPT-5.5’s evaluations.
From $200 to $30: Five Layers of LLM Cost Optimization A walkthrough of how I cut an LLM-based product classifier's token usage by ~92% through compression, two-stage prompting, exact-match lookups, similarity caching, and batching.
