#context-windows

#context-windows

While new models with more parameters and better reasoning are valuable, models are still limited by their lack of working memory. Context windows and improved memory will drive the most innovation in agentic AI next year, by giving agents the persistent memory they need to learn from past actions and operate autonomously on complex, long-term goals. With these improvements, agents will move beyond the limitations of single interactions and provide continuous support.

Context engineering has emerged as one of the most critical skills in working with large language models (LLMs). While much attention has been paid to prompt engineering, the art and science of managing context-i.e., the information the model has access to when generating responses-often determines the difference between mediocre and exceptional AI applications. After years of building with LLMs, we've learned that context isn't just about stuffing as much information as possible into a prompt.

Following a week of major AI programming announcements from Microsoft and Google, OpenAI has joined in the fun. Today, OpenAI is announcing a new version of Codex, its programming-focused AI model. While the announcement was today, the actual GPT-5.1-Codex-Max capability will be available tomorrow in Codex for ChatGPT Plus, Pro, Business, Edu, and Enterprise users. API access is "coming soon." OpenAI says the new Max model "replaces GPT-5.1-Codex as the recommended model for agentic coding tasks in Codex and Codex-like environments."

Context windows are huge and using them well has been a difference-maker for me. I get the best results when I have one conversation for each project.