Articles from antirez.com

Programmers should steer AI by defining ideas and designs, not by reviewing generated code, to focus on higher‑level decisions and quality.

LLM agents can perform manual QA testing via markdown instructions, catching regressions and psychological issues, raising software quality beyond traditional automated tests.

Antirez spent four months building a new Redis Array data type, using AI to achieve a complexity he would have otherwise skipped.

Antirez argues that AI is fundamentally reshaping programming, citing his own experience using Claude Code to complete tasks in hours that would have taken weeks, and urges developers to embrace the change.

Antirez argues LLMs are not stochastic parrots, that reinforcement learning will drive further scaling, and that chain-of-thought improves output by enabling internal search and learned reasoning steps.