Notes on Building Software
The kind of thing we'd tell a founder on a call — concrete, honest, and free of hype.
Ox Alpha Was GLM-5.3-Flash: Specs, Price, and How to Use It
Ox Alpha was the free stealth model on OpenRouter. Z.ai confirmed it as GLM-5.3-Flash on 26 August 2026. Specs, benches, current pricing, and the model IDs that still work.
Read it →Grok 4.6: Tied with GPT-5.6 Sol, Same $2/$6 as 4.5
SpaceXAI shipped Grok 4.6 on 12 August 2026. It scores 61 on Artificial Analysis, tying GPT-5.6 Sol, at $2/$6 per million tokens. The benchmarks, the cache-price catch, and where we'd actually use it.
Read it →DeepSeek V4 Flash 0731: Cheap, Fast, and Hard to Steer
DeepSeek's V4 Flash 0731 costs $0.14 per million input tokens and beats V4 Pro Preview on every agent benchmark they published. The numbers, the instruction-following problem nobody benchmarks, and what it takes to self-host.
Read it →Shopify vs Custom Build: When Each Is Actually Right
Most brands should stay on Shopify. A few genuinely shouldn't. The limits that decide it, what each route costs, and the middle option teams skip.
Read it →Claude Opus 5 vs Grok 4.5 vs GPT-5.6 Sol: What Changed for Builders
Claude Opus 5 landed on July 24 at $5/$25 per million tokens with a 1M context. How it compares to Grok 4.5 and GPT-5.6 Sol on price, benchmarks and independent testing — and what you'll have to change in your prompts.
Read it →Kimi K3: What an Open-Weight Frontier Model Means for Builders
Moonshot AI's Kimi K3 lands this week — a 2.8-trillion-parameter open model with a 1M-token context and native vision. An honest read on what it changes if you're shipping a product, and where the caveats are.
Read it →How to Hire an AI Development Agency Without Getting Burned
The AI gold rush produced a lot of demos and not much production. How to tell a team that ships real AI from one that can only impress in a sales call.
Read it →How to Choose a White-Label Development Partner
For agencies handing client work to a dev partner: what to check before you trust someone, the red flags, and fixed-scope vs dedicated developers.
Read it →LangChain vs LangGraph: Which Does Your AI Project Need?
LangChain and LangGraph solve different problems. A plain-English guide to when a chain is enough and when you need a graph, with a real 12-step agent example.
Read it →How Much Does an MVP Cost in 2026? An Honest Breakdown
There's no standard MVP price, and anyone quoting one before scoping is guessing. What drives the number, real reference points, and a figure you can trust.
Read it →Practical notes on shipping software
Occasional, concrete write-ups on building AI, web and mobile products: the kind of thing we'd tell a founder on a call. No spam, unsubscribe anytime.