Blog

Most moderation, routing, and triage calls aren't generation problems. Clef proves it by answering in 38.8 milliseconds instead of seconds.

••3 days ago

Cloudflare's Clef: When a Decision Model Beats an LLM Call

Most moderation, routing, and triage calls aren't generation problems. Clef proves it by answering in 38.8 milliseconds instead of seconds.

Kiril Urbonas·4

Mods make Claude Code a real runtime you can program. They also run with your full native permissions, no sandbox, so a bad one is a bad CI step.

••4 days ago

Claude Code Mods: Programmable, Unsandboxed, and Your Problem in CI

Mods make Claude Code a real runtime you can program. They also run with your full native permissions, no sandbox, so a bad one is a bad CI step.

Google shipped a 1M-token output ceiling and strong cyber-defense benchmarks, then handed the keys to almost nobody. Here is what that gating pattern tells you.

••5 days ago

Gemini 4 Argon: A Frontier Model You Mostly Can't Use Yet

Google shipped a 1M-token output ceiling and strong cyber-defense benchmarks, then handed the keys to almost nobody. Here is what that gating pattern tells you.

OpenAI priced GPT-6.1 Sol at a fifth of GPT-6 Astra and called it nearly as good at agentic coding. That claim is now a routing decision, not a headline.

••6 days ago

GPT-6.1 Sol's 80% Price Cut Rewrites Agentic Coding Math

OpenAI priced GPT-6.1 Sol at a fifth of GPT-6 Astra and called it nearly as good at agentic coding. That claim is now a routing decision, not a headline.

A slow database made a backend service look dead, and the health check that was supposed to protect it killed it faster. The lesson has nothing to do with AI.

Azure OpenAI's Sweden Central Outage: A Health Check Postmortem

A slow database made a backend service look dead, and the health check that was supposed to protect it killed it faster. The lesson has nothing to do with AI.

Same sticker price, a real-world cost drop from speed and token efficiency. Here is who should move today and who can wait a sprint.

Claude Sonnet 5.5: Should You Switch From Sonnet 5

Same sticker price, a real-world cost drop from speed and token efficiency. Here is who should move today and who can wait a sprint.

Kiril Urbonas·4

Microsoft's Storm-3068 report used zero malware to steal Kubernetes credentials, just a password reset, a pipeline edit, and permissions nobody had scoped down.

Storm-3068: A CI/CD Pipeline Is a Kubeconfig Exfiltration Machine

Microsoft's Storm-3068 report used zero malware to steal Kubernetes credentials, just a password reset, a pipeline edit, and permissions nobody had scoped down.

Docker put AI coding agents in hosted microVMs instead of containers, because a container was never the isolation boundary this job needed.

Docker Cloud Sandboxes: Why Agents Need MicroVMs, Not Containers

Docker put AI coding agents in hosted microVMs instead of containers, because a container was never the isolation boundary this job needed.

Google's benchmarks show a 70B model restoring in 37 seconds instead of minutes. The catch is a hash and a hardware match that silently refuses to restore when either is off.

GKE Pod Snapshots: Cold Starts Drop 89%, If Your Nodes Match

Google's benchmarks show a 70B model restoring in 37 seconds instead of minutes. The catch is a hash and a hardware match that silently refuses to restore when either is off.

Zed says agents made pull requests obsolete and shipped Delta to replace them. The review unit needs rethinking, but review itself, and the gates around it, stay.

Zed Delta and the Pull Request: Obsolete, or Just Overloaded?

Zed says agents made pull requests obsolete and shipped Delta to replace them. The review unit needs rethinking, but review itself, and the gates around it, stay.

Kiril Urbonas·15

CERN is moving accelerator control computers to Debian because RHEL raised its minimum CPU level. Check your own fleet's x86-64-vN support before the next OS upgrade does it for you.

CERN Left Red Hat for Debian: The CPU Baseline Lesson

CERN is moving accelerator control computers to Debian because RHEL raised its minimum CPU level. Check your own fleet's x86-64-vN support before the next OS upgrade does it for you.

Kiril Urbonas·20