What if iteration is all we need?

What if every ceremony in software development was a workaround for expensive human iteration? What happens when juniors learn architecture on day one and spec-driven development turns out to be waterfall in disguise? Are we in the best restaurant in the world, but there’s no menu?

Same Loop, Different Name?

ThoughtWorks’ agentic engineering retreat findings and the elastic loop

How Does Truffle Taste? The Elastic Loop in Agentic Engineering

Agentic engineering fails when loops don’t close. A talk about tight feedback, loose delegation, and what your organization’s mirror actually reflects.

Personal AI is Already Here (And You’re Probably Not Ready)

Three weeks with OpenClaw on a Raspberry Pi. And a glimpse at what’s coming for software architecture.

Der Assistent ist tot: Zweitausend Agenten bauen einen Browser

Zweitausend Agenten bauen parallel einen Webbrowser – Tausende Commits pro Stunde. SQL schlägt Bash bei strukturierten Agenten-Abfragen mit 100 vs. 53 Prozent Genauigkeit. Plus: Selbst Karpathy fühlt sich im Agentic Engineering abgehängt.

90% von allem ist Schrott – und das war schon immer so

Ein forschender Agent liest 1500 Papers und repliziert unveröffentlichte Alzheimer-Forschung. 90% von allem war schon immer Schrott – KI macht ihn nur sichtbar. Plus: Distributional Convergence erklärt, warum Modelle ohne Führung im Generischen landen.

Agentic Pelican on a Bicycle: Claude Opus 4.5

Last week, I declared a clear winner: Gemini 3 Pro. Just one week later, Opus 4.5 shows comparable improvements when iterating on its zero-shotted pelican on a bicycle. I like how Opus 4.5 added improvements that make sense. Where 4.1 added a plate with a selection of

Agentic Pelican on a Bicycle: Gemini 3 Pro

Looks like we have clear winner when it comes to agentically iterating on Pelican on a Bicycle (Simon’s OG benchmark). Let Gemini 3 speak for itself: For each iteration, I converted the SVG to a JPG using the chrome CLI and inspected the result using take_screenshot to simulate

Agentic Pelican on a Bicycle

The agentic loop—generate, assess, improve—seems like a natural fit for iterating on pelicans on bicycles.

Wenn der Agent das Labor betritt

Ein Agent mit XR-Brille begleitet Genexperimente im Wet-Lab physisch. Kleine Teams mit Agenten rütteln an der Firma als Konzept. Plus: Einzelpersonen mit KI erreichen Qualität von Zweierteams ohne.

Claude Skills, anywhere: making them first-class in Codex CLI

Make Claude Skills work in other agents like Codex by adding the missing piece: a small enumerator script.

Fire Your Fetch Tool — Let your Agent Use a Browser

“Fetching a URL” sounds trivial, but inside an agent it can get messy. Part of the confusion comes from documentation that blurs what each web tool actually does. Remember when our dear agents didn’t even bring anything with them? With Codex, the situation is still less clear than with