
Is Jev Really Faster for Browser Automation? I Measured It
I benchmarked the Jev model against an LLM agent on real browser navigation: 13x faster per task, and one setup mistake that broke every single test.
Platform engineering, Go, DevOps, and applied AI.

I benchmarked the Jev model against an LLM agent on real browser navigation: 13x faster per task, and one setup mistake that broke every single test.

jev is an open-source CLI for TypeSafe AI's Jev model: ask any text a typed question, get a calibrated probability back, and branch on the exit code.
Claude Code doesn't tell you where your tokens, money, or time went. Here's the weekly review habit I built with Agento, a free, open-source local dashboard for your Claude Code sessions.

Use Moonshot's Kimi K3 and Z.AI's GLM coding plan subscriptions in Claude Code without per-token API billing, through the open-source Ferrox LLM gateway. Full setup guide.

A look at why systems thinking matters in engineering, and a recommendation for Adam Korga's Fuckup Almanac and IT Dictionary.

A practical 2026 guide to protecting your software supply chain. Lockfiles, postinstall hardening, OIDC scoping, package provenance, model safety, and incident response, with real incidents and references.
A first-hand review of Gartner Predicts 2026: Intelligent Applications. Five predictions, the numbers behind them, and what enterprise application leaders should actually do next.

Every AI-native enterprise needs a GenAI Platform Team to build the harness: the engineering layer around the model that makes agents safe, observable, and economical at scale.

Wire a Slack CLI into Claude Code, Cursor, and Codex in 10 minutes — read channels, post messages, summarise threads. xoxc browser tokens for personal automation, OAuth apps for production.

Embedded vector databases for Go in 2026 — chromem-go vs sqlite-vec vs Bleve vs LanceDB-go. Benchmark (latency, recall@10, memory), decision matrix, and a full RAG walkthrough.