Claude, ChatGPT and Gemini compared.
The same brief run on each new model, with the time, the tokens and the cost side by side. Which model to use for which job, from real builds.
You don't need a strong model to build
The businesses getting real value from AI use the same models, wired differently. What "agentic" means, three real examples and a 90-minute exercise.
25 Sept 2026 · 5 min
AI helped me message 239 people. One in seven said yes.
I tested Jev, a small AI model, on my own LinkedIn outreach: 239 personal messages over two days, and one in seven said yes. Plus GPT-6 Astra vs Opus 5.5.
24 Sept 2026 · 7 min
What kind of model is GPT-6 Astra?
Frontier models launch as opportunity models and end up efficiency models. Astra rebuilt my 2011 building, and the tables show which model does which job.
10 Sept 2026 · 5 min
Three AI models, one brief: what each build actually cost
Fable 5.1, GPT-5.6 Sol and Gemini 3.8 Flash each built the same site from the same CV. The runs cost $23.57, $10.20 and $1.48. The harness still decides.
3 Sept 2026 · 4 minGet Build Notes by email
A few emails a month.