This approach resolves remote micro-frontends (MFEs) via a same-origin proxy mechanism directly on Cloudflare’s edge network, completely avoiding CORS issues in production while preserving a native development experience locally. In this example of monorepo architecture, we split our system into…
I wanted a model that is both free to run and small enough to fit in the ~50 MB memory budget of a Worker. After testing a few options locally I settled on MiniLM‑Chat‑6B from Hugging Face, exported to the…
I turned on vLLM speculative decoding on a Friday afternoon, ran my usual one-request benchmark, and watched tokens per second jump from about 48 to about 88. I wrote "1.8x free speedup" in the team channel. On Monday, with real traffic hitting the…
Agentic LLM systems have moved from linear prompt chains to graph-based workflows and, more recently, code-executing harnesses. Chains are simple but fragile, graphs add branching, retries, and validation, and code harnesses verify outputs through execution. The article advises validating model…
14:47 UTC, Tuesday. Pods in the checkout-api deployment start OOMKilling in a loop, three or four at a time, in the middle of an ordinary afternoon. Traffic is flat. No deploy went out today. PagerDuty fires on KubePodCrashLooping, not on anything…
This edition is running a bit late. I was sick last week, and it seems that sorting through two Gutenberg releases and a month of Make posts is harder while laid out on the couch. I’m on the mend now,…
A minimum-access setup should not depend on a shared account that someone has to look after.” For day-to-day work, each user signs in with their own Microsoft account. They see exactly the files SharePoint already lets them see, and nothing…
Artificial intelligence is spreading across the world, but not at the same speed everywhere. The countries that build the most advanced AI models are not always the countries where the most people use AI. Microsoft estimates that 18.8% of the world’s…
QCon AI New York (December 15-16, 2026): Learn how senior engineers are building AI systems that hold up in production. Register Now Agentic LLM systems have moved from linear prompt chains to graph-based workflows and, more recently, code-executing harnesses. Chains are simple…
QCon AI New York (December 15-16, 2026): Learn how senior engineers are building AI systems that hold up in production. Register Now Agentic LLM systems have moved from linear prompt chains to graph-based workflows and, more recently, code-executing harnesses. Chains are simple…
Ecosystems, services, and cost optimization across the big three clouds.
An article joins this feed when it matches these terms. Each one is also a search of its own.