llms.blog
AI

OpenAI's Computer History turns your Mac activity into a searchable ChatGPT memory

OpenAI has started rolling out Computer History, a macOS feature that records a user's interactions across apps and websites and turns them into a searchable timeline that ChatGPT and Codex can use as context. Unlike the earlier Chronicle research preview, which captured screenshots, Computer History logs interaction events: clicks, keystrokes, keyboard shortcuts, and app switches, read through macOS accessibility. OpenAI says it does not capture screenshots, screen recordings, microphone input

axc
axc
2 min
OpenAI's Computer History turns your Mac activity into a searchable ChatGPT memory

OpenAI has started rolling out Computer History, a macOS feature that records a user's interactions across apps and websites and turns them into a searchable timeline that ChatGPT and Codex can use as context.

Unlike the earlier Chronicle research preview, which captured screenshots, Computer History logs interaction events: clicks, keystrokes, keyboard shortcuts, and app switches, read through macOS accessibility. OpenAI says it does not capture screenshots, screen recordings, microphone input, or system audio, and it never includes private browsing.

openai-computer-history-tracks-clicks-keystrokes

The recorded events are periodically summarized into text and stored locally as Markdown memory files. The timeline view groups those summaries by day and time and shows which apps were involved.

When ChatGPT notices a repeated workflow, it can suggest a Skill or automation, and Codex can build a reusable template from the recorded steps. OpenAI cites finding recently edited documents and generating standup summaries as examples.

Access is gated. In Business and Enterprise workspaces an admin must enable the feature, then each user must consent individually, and the Memories feature has to be turned on. Users can set include and exclude lists and pause or resume recording from the menu bar. It is not yet available in the European Economic Area, Switzerland, or the United Kingdom.

The privacy limits are real. Temporary event files sit inside the ChatGPT app group and are deleted after 48 hours, but the memory files remain on disk as plaintext Markdown and are not encrypted, so any program running under the same macOS user could read them. OpenAI processes the temporary files on its servers but says it does not retain them unless required by law, and does not use them for training, though later chats that include those memories as context may still become training data depending on a user's settings.

OpenAI's own documentation flags a heightened prompt injection risk, because Computer History can pull untrusted web content into a model's context.

Sources

The Decoder: https://the-decoder.com/openais-computer-history-turns-your-clicks-and-keystrokes-into-a-searchable-chatgpt-memory-timeline/

OpenAI docs: https://learn.chatgpt.com/docs/integrations/computer-history

AILLMOpenAIPrivacyMacOS
ShareX (Twitter)LinkedIn

Written by

axc

More to read

  • Group Relative Policy Optimization (GRPO): How Eliminating Value Models Scaled LLM Reasoning

    Post-training reinforcement learning (RL) has become the primary mechanism for scaling reasoning capabilities in large language models. While early reinforcement learning from human feedback (RLHF) focused on conversational style and safety alignment, extending RL to multi-step reasoning domains such as mathematics, algorithmic coding, and formal logic exposed critical limitations in classical algorithms. Standard Proximal Policy Optimization (PPO), long the foundational algorithm for instructi

    1 min

  • Document Parsing and Visual Retrieval for Production RAG: Architecture, Benchmarks, and Serving Trade-Offs for Docling, Marker, MinerU, and ColPali

    Document Parsing and Visual Retrieval for Production RAG: Architecture, Benchmarks, and Serving Trade-Offs for Docling, Marker, MinerU, and ColPali The retrieval quality of a Retrieval-Augmented Generation (RAG) system is strictly bounded by the fidelity of its document ingestion pipeline. In enterprise environments, the vast majority of domain knowledge remains locked in unstructured Portable Document Format (PDF) files, scanned reports, technical manuals, and multi-column research papers. Na

    1 min

  • Context Window Extension in Large Language Models: How Position Interpolation, YaRN, and LongRoPE Scale Sequence Lengths

    Large language models are bounded during pretraining by a fixed sequence length, typically between 2,048 and 8,192 tokens. When standard autoregressive transformers attempt to process sequences beyond this pretraining context window, performance degrades immediately. Perplexity rises sharply and the model loses coherence within a few dozen tokens past the training boundary. Extending this context window by training from scratch on long sequences is computationally prohibitive due to the quadrat

    1 min