OpenAI Limit Resets and Prompt Engineering Guide

新智元 · wechat · 2026-07-15

Active users for OpenAI's Codex and ChatGPT Work have reportedly exceeded 8 million. Following this, the official limits were reset again, and the rate-limiting strategy changed from a 5-hour window to daily refreshes. The article also summarizes the core of OpenAI's new prompt engineering guide: avoid long prompts, focus on the four elements of "outcome, constraints, evidence, and acceptance criteria," and remove redundant rules, useless examples, and steps the model already knows.

Citing official tests, the article notes that streamlined prompts can improve scores by 10% to 15%, reduce token consumption by 41% to 66%, and cut costs by up to two-thirds. The author emphasizes that collaborating with models is shifting from "hand-holding" to "issuing commands."

Related event: Codex Developer Update: GPT-5.6 and Parallel Tasks(28 posts)→

Original post →

More from Models

Models channel →