I spent three months in 2024 building retry logic for a pipeline that extracted product data from GPT-4.
Someone analyzed 3,007 Claude Code sessions and found a ratio that broke my brain: for every fresh token sent to the API, 525 tokens were served from cache.
OpenAI dropped GPT-5.4 on March 5, and the headline number — 75% on OSWorld-Verified, beating the 72.
The single most repeated piece of prompt engineering advice from 2023 is now actively degrading your outputs. "Think step by step.
OpenAI pulled the plug on Sora this week. The app goes dark in April; the API follows in September.