25 Min Read

Status: Promise delivered ✅ The Doors Are Open A little over a month ago, I published...

10 Min Read

TL;DR Welcome back to Dev Opportunity Radar! This is a weekly series where I share opportunities,...

7 Min Read

How I pair-programmed with Google Antigravity powered by Gemini 4 Argon to build a zero-dependency Go TUI and OpenTelemetry/Prometheus observability stack for Oracle Databases and Linux SAN storage.

10 Min Read

Serverless DuckDB on Google Cloud, in your own project. Files on GCS, tables in BigQuery (read and write), what I measured, and what I learned.

10 Min Read

What actually shipped across Build, Scale, Govern, and Optimize — and what I'd tell a team starting...

1 Min Read

👋👋👋👋 Looking back on your week -- what was something you're proud of? All wins count -- big or small...

11 Min Read

The same Tesla T4 on the same Google Cloud VM decoded Gemma 4 E2B at 115 tokens/s at 45 °C and 107 at 77 °C. The card sits at its 70 W limit, a hotter chip draws more power at the same clock, so the clock drops. No thermal throttle fires, and no spec sheet mentions it.

3 Min Read

The Grace Hopper Celebration has been around since 1994, and for a lot of people, it's the event for...

19 Min Read

Yes. Speculative decoding with Google's 59 MB QAT multi-token prediction (MTP) drafters speeds up Gemma 4 E4B 1.72x and E2B 1.40x on an 8 GB RTX 3050, and 1.49x and 1.18x on a 4 GB laptop GTX 1650 Ti, served by llama.cpp one request at a time, with unchanged GSM8K and BFCL scores.

7 Min Read

TLDR: A brief summary of how I got here. The Mindset For the last 3 years, I have been...

10 Min Read

Fourteen Apache-2.0 and MIT open-weight models that fit one TPU v5e chip, served one after another through vLLM on the same pinned image and scored on GSM8K and BFCL against Gemma 4 E2B. Qwen3-4B matches Gemma's accuracy at 0.57x its output, SmolLM3-3B and Granite 3.3 2B match it on tool calls, and Gemma keeps the lead on long prompts.

7 Min Read

If you have been following me for a long time, you already know that I have been holding off on my...

4 Min Read

We are so excited to announce the winners of the Hacktoberfest Open-Source AI Challenge: Touch...

21 Min Read

How I designed, connected, scaled, governed, evaluated, and QLoRA fine-tuned an enterprise SecOps & FinOps agent on Google Cloud.

8 Min Read

Why your agents need their own identity Most teams run every AI agent under one shared...

26 Min Read

Why do 200-line agent prompts, Asimov's Three Laws, and sequential pre-landing checklists all fail the same way? How Fernando Flores's 1986 Committed Speech, Nuel Belnap's 1977 4-Valued Logic, and Tony Hoare's 1978 CSP turned our Makefile and init.d workflow into a self-healing Commitment Machine.