Before You Add an AI Reviewer, Add These Checks
Anthropic's AI code review works because flags and fast rollback sit under it. A small team should first add checks an agent can't talk into a pass.
Writing · Tag
Posts tagged AI
55 posts on AI, page 1 of 5. Or browse the full writing index →
Posts tagged AI
Anthropic Moved Its Monorepo to Scion. You Shouldn't.
Anthropic built Scion and moved its monorepo off git in five months. Here is why a small team shouldn't copy it, and where to spend the attention instead.
Who Buys Anything When Robots Do the Work?
If robots do the work and nobody earns, who buys? I think the economy dies slowly and the company store fills the gap. That's where I think it goes.
Why I Doubt UBI Is Coming
Tax all US output at 100% and it comes to about $95,000 a person a year. Why I doubt UBI arrives, and think robots become the measure of wealth.
We Gated the Code and Left the Prose Wide Open
Teams built real review gates around agent-written code. The PR descriptions, design docs, and incident summaries the same agent writes pass through nothing.
DHH's Rails World 2026 Keynote: Pencils Down, Now What
DHH told Rails World 2026 that hand-writing code no longer pays. What he gets right, what Basecamp 5 proves, and who owns the code nobody reads.
How to Actually Make Money With AI in 2026: An Engineer Ranks 13 Side Hustles
An engineer who builds AI systems ranks 13 ways to make money with AI in 2026 by ceiling, moat, time to first dollar, and fulfillment burden.
Multi-Agent AI Teams Agree Their Way Into Garbage
I set two agent frameworks loose on real work in team-of-agents mode. They agreed their way into the wrong product. The research says exactly why.
Anthropic's Extreme Scenario Has a Precondition
Anthropic published an economic upside scenario and an alignment risk admission the same week. The upside needs the thing nobody has a plan for.
Agents Don't Need Prompts. They Need Managers.
Agents stop before the work is done, not because the model is lazy but because nobody built the management system a human employee gets for free.
Building an LLM Audit Trail That Passes SOC 2
An append-only Ecto schema for LLM calls, the fields an auditor actually samples, and why provider request IDs are what makes an entry defensible.
Throttling LLM Calls in Elixir Before You Hit 429
LLM providers cap tokens per minute too, and you can't count a response's tokens before it lands. Size a Hammer bucket that never sends the call that 429s.