📰 Dev.to · Rob

The results already shipped. This is the part that took longer: forking an open-source Home Assistant benchmark, extending it into calendar, portfolio, and codi

115 days after building this blog from a cabana in Cabo, I spent one afternoon — 2:54 PM to 6:23 PM, back to back — running a chain of admin panel improvements:

The May audit closed clean. Since then we shipped an MCP server, a Slack integration, and a shareable-snippet image generator -- three new pieces of attack surf

A challenge to a coding agent: prove whether months of homegrown test harnesses and bakeoff scripts were reinventing wheels that already exist. A survey of what

I put Qwen 3.6 27B, Qwen 3.6 35B-A3B, Qwythos-9B, GLM-4.7-Flash, and Nemotron-3-Nano through the same real coding task on my homelab RTX 5090. Along the way I h

Back in Q1 I read a headline about Google cutting AI memory use 6x and filed it under "watch and revisit." Four months later, Google still hasn't shipped offici

Anthropic and AWS are both, underneath everything else, infrastructure providers renting out specialized compute. But the sharper parallel is behavioral — both

A gloomy Cape Cod afternoon post-July 4th turns into a deep dive on ComfyUI, Lemonade Server, and LocalAI — plus llama-benchy and AMD's AI Playbooks — and the c

GLM is suddenly everywhere in developer conversations. Before we run the bakeoff, we need to answer two questions: what is GLM, and is it suitable for a single

A finance intern is spending her summer observing business processes and vibe coding automation tools. Not a CS major. Not shadowing someone. Building something

Vibe coding has moved from hobbyist curiosity to enterprise rollout across knowledge workers, and the next wave of AI adoption will be defined by governance and

Almost all of your AI coding agent's token waste comes from five mechanical leaks — cache misses, context bloat, idle MCP servers, oversized models, and an unwa

Providers have every reason to serve a smaller or more quantized model under load. I ran the experiment to see if you can catch it from the outside. The obvious

Four frontier models, ten tasks, one government shutdown. We ran Claude Fable 5 through the homelab benchmark harness three hours before Anthropic pulled the pl

Two Discord bots, one 14B model, five fitness-tracker tasks. Both agents failed on the first try. Getting them working required debugging context overflow, sile

I specced an on-chain credit ledger for a compute network and the token program refused to initialize the mint. That rejection sent me back to the design. The l

A model refresh on the homelab (Qwen 3.6, new embeddings, 469 llama.cpp builds), a feature sprint on the vacation planning site (calendar sync, expense tracking

I built a trip planning site for my F1 Montreal group. Then I ripped out every hardcoded value, added a setup wizard, ran a security audit, and open-sourced it.

Every week or two, a model drops that makes the local AI community lose its collective mind. This...

Two models. Same prompt. Same five fodder files. Same 27 published posts to check for redundancy....

In Round 1, we ran five local models and two cloud models through a single coding task. The local...

Two days ago, Gemma 4 couldn't finish a feature. Today it built one, pushed it to GitHub, and it's...

A deep audit of vibescoder.dev revealed that Cloudflare was silently blocking every major AI crawler — even after we'd explicitly turned that setting off. Here'

Two days ago, Gemma 4 topped our local model benchmark — 167 tokens per second, perfect code quality...