Custom instructions for ChatGPT
Summary
OpenAI is introducing custom instructions for ChatGPT, allowing users to set persistent preferences and requirements that the model will consider across all conversations. The feature launches in beta for Plus plan users and will expand to all users in coming weeks.
View Cached Full Text
Cached at: 04/20/26, 02:54 PM
Similar Articles
Personalizing ChatGPT
OpenAI's Academy announces personalization features for ChatGPT including Custom Instructions and Memory capabilities that allow users to customize ChatGPT's behavior and have it remember user preferences across conversations.
Using custom GPTs
OpenAI Academy guide on building custom GPTs—purpose-built ChatGPT versions for specific tasks and workflows. The guide covers when to use custom GPTs, how to set them up through the GPT builder, and best practices for defining instructions, knowledge bases, and capabilities.
ChatGPT plugins
OpenAI is launching ChatGPT plugins, enabling the model to access real-time external information and perform actions via third-party integrations, starting with ChatGPT Plus subscribers and select early collaborators. The rollout also includes the ability for developers to build their own plugins, with plans to expand plugin support beyond ChatGPT to other OpenAI model applications.
Introducing ChatGPT
OpenAI introduces ChatGPT, a conversational AI model fine-tuned from GPT-3.5 using reinforcement learning from human feedback (RLHF). The model is designed to answer follow-up questions, admit mistakes, and reject inappropriate requests, with free access provided during the research preview.
Memory and new controls for ChatGPT
OpenAI is rolling out memory improvements to ChatGPT, now available to free users, allowing the model to reference past conversations for more personalized responses. Users can control memory settings, including toggling saved memories and chat history on or off.