Dev Blog

Building an AI chicken guardian, one hack at a time.

all agents ai chickens chookbench claude community experimentation experiments local-llm meta multi-agent vibe-coding vision
April 11, 2026 · 9 min read
You Can Just Run the Experiment
I had a hunch about multi-agent AI. A few years back I'd have argued about it online. This time I just ran the experiment -- and so can you.
ai agents experimentation multi-agent
April 11, 2026 · 7 min read
The Coop Was Always an Excuse
I thought I was building a chicken coop monitor. Turns out I'm running a long-running experiment in applied AI, and the chickens are the case study.
ai agents meta chickens
April 7, 2026 · 10 min read
Claude vs Local Models: Is the Frontier Worth It?
We ran Claude Sonnet 4 through the same chicken coop benchmark as our local models. The scores are surprisingly close -- but the experience of getting there couldn't be more different.
chookbench claude local-llm vision experiments
April 6, 2026 · 9 min read
Local Vision Showdown: Can Open-Source Models Watch Chickens?
We pitted qwen-3.5-35b against gemma-4-26b on chicken coop observation tasks. The results reveal complementary strengths, surprising failure modes, and one critical setting that makes or breaks everything.
chookbench local-llm vision experiments
March 29, 2026 · 9 min read
The Three Layers of AI Progress (And the One You Can Actually Work On)
Hardware, model training, and application -- three layers of AI improvement. Two are locked behind billion-dollar labs. The third is wide open, and casual vibe coders are doing some of the most interesting work.
ai agents vibe-coding community