Slow down to speed up: so much has changed in 6 months’ time
Source
Gergely Orosz
Author
Gergely Orosz
Date
Key takeaways · AI-distilled
Claude Code's creator runs roughly five agents in parallel and ships 20-30 pull requests a day. Inside Anthropic, written product requirement docs have been replaced by prototypes, and Claude Cowork was built in ten days.
Average pull request size is up 3x in 18 months. Review load therefore grows faster than PR count, and the bottleneck moves from writing code to having anyone left who can read it.
Meta's cuts landed unevenly: Instagram's design team lost 44% of headcount, developer documentation and support lost 95%, and senior integrity staff were reassigned to AI data-labeling work.
DHH reversed his own position that AI should not write code directly. His resistance was about model quality — he used to spend longer rewriting the output than writing it himself, and that arithmetic flipped.
Terms in this piece · Glossary
grounding — Tying a model's answers to checkable sources — retrieved documents, live data, tool results — instead of letting it answer from memory alone.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Why it matters
A groundingTying a model's answers to checkable sources — retrieved documents, live data, tool results — instead of letting it answer from memory alone.Full definition → field report on how top labs and companies are restructuring engineering around the newer generation of coding agents, plus a concrete cautionary example (Meta's account-takeover AI bug) that surfaces real risks of shipping AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → features too fast.
Key quotes
“The models released in November 2025 elevated agents to being genuinely useful. We"”
“Meta has been destroying its engineering org, and an obsessive focus on AI seems to be one reason for it.”
