The amount of software I can create is now mostly limited by inference time and hard thinking. I can ship code now at a speed that seems unreal.

2025 was an exciting and mildly surprising year of LLMs. LLMs are emerging as a new kind of intelligence, simultaneously a lot smarter than I expected and a lot dumber than I expected.

GPT-4 was the unlock for chat, Sonnet 3.5 was the unlock for code, and now Opus 4.5 is the unlock for agents.

Claude Opus 4.5 is the best model currently available. It is the most intelligent and capable, most aligned and thoughtful model. It is a joy.

Vibe engineering establishes a clear distinction from vibe coding. It’s also become clear to me that LLMs actively reward existing top tier software engineering practices.