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)→
More from Models
- Fern 0.1 debuts: a model built to audit training data and debug agent traces for AI builders — bneyshabur · 2026-10-26
- Fern 0.1 posts 73.4 on SWE-Bench Verified, far behind frontier models on agentic benchmarks — bneyshabur · 2026-10-26
- Fern's "context is intelligence" thesis: prediction keeps improving out to 10.2M tokens — bneyshabur · 2026-10-26
- Mirendil launches Fern, a from-scratch pretrained model with up to 10M-token context — bneyshabur · 2026-10-26
- Users spot a dedicated translation UI appearing in Claude — BLCNYY · 2026-10-26
- GrokBot user: flight booking and shopping all blocked, agent can't do anything useful — lucasmeijer · 2026-10-26