Memory and new controls for ChatGPT

Dreaming: Better memory for a more helpful ChatGPT

ChatGPT introduces a new memory system to better remember preferences, keeping context fresh and relevant across conversations.

Personalizing ChatGPT

Learn how to personalize ChatGPT using custom instructions and memory to get more relevant, consistent, and tailored responses.

New ways to manage your data in ChatGPT

ChatGPT users can now turn off chat history, allowing you to choose which conversations can be used to train our models.

Custom instructions for ChatGPT

We’re rolling out custom instructions to give you more control over how ChatGPT responds. Set your preferences, and ChatGPT will keep them in mind for all future conversations.

ChatGPT can now see, hear, and speak

When Should Memory Stay Silent: Measuring Memory-Use Boundaries in Memory-Augmented Conversational Agents

arXiv:2606. 06055v1 Announce Type: new Abstract: Long-term memory enables language model agents to support personalized interactions, but it remains unclear when available memories warrant integration into responses.

Mitigating Over-Personalization in LLMs via Structured Memory

arXiv:2608. 08300v1 Announce Type: new Abstract: Conversational assistants increasingly rely on persistent long-term memory to personalize responses across sessions.

PersistBench: When Should Long-Term Memories Be Forgotten by LLMs?

arXiv:2602. 01146v2 Announce Type: replace Abstract: Conversational assistants are increasingly integrating long-term memory with large language models (LLMs).

Don't Scroll Back: Missing-Evidence Memory for Streaming Dialogue Summarization

Users of modern platforms repeatedly need summaries of recent dialogue, but the window rarely contains enough context to be interpreted on its own. We formalize this setting as streaming dialogue summarization, where a system must summarize a current window using selective memory from an unbounded history under a fixed budget.

RUMBA: Russian User Memory Benchmark

arXiv:2607. 21447v1 Announce Type: cross Abstract: The ability to handle long-term memory in LLMs is becoming increasingly critical, yet existing benchmarks remain English-centric and rely on aggregate retrieval metrics, failing to capture interactions between long-range context, temporal information, and reasoning.

ChatGPT for managers

Learn how managers use ChatGPT to prepare for conversations, write clear feedback, stay organized, and improve team effectiveness.

GPT-5.5 Instant: smarter, clearer, and more personalized

GPT-5. 5 Instant updates ChatGPT’s default model with smarter, more accurate answers, reduced hallucinations, and improved personalization controls.