Chronicle
Summary
Chronicle is a voice-based personal memex tool that helps you remember everything by recording and organizing your spoken thoughts.
Similar Articles
@op7418: Codex keeps getting better—new Chronicle memory continuously takes local screenshots so it knows which doc or bug you mean without you spelling it out. Pro users only for now.
Codex adds Chronicle, a local screenshot-based memory feature that lets it track open docs and bugs without explicit context.
@lxfater: Codex has a feature I think is great but nobody uses – Chronicle. Once enabled, Codex continuously takes screenshots of your screen and gains massive context. The benefit of massive context is that you don't need to feed it redundant information. Its answers and assistance become more personalized, and it gets better the more you use it.
Codex's Chronicle feature, once enabled, continuously screenshots your screen, providing massive context, making answers more personalized and easier to use over time.
OpenAI reinvents Recall except everything is stored remotely
OpenAI introduces Chronicle, an opt-in research preview for ChatGPT Pro users that captures macOS screen context to enhance Codex memory, reducing the need to restate context during development workflows.
@yoyo__AI: Automatically distill yourself with a single Codex prompt, fully automate daily repetitive tasks. Steps: Open Codex Settings → Personalization → Memory → Enable Chronicle. Enter the prompt: Review my Chronicle memory, find workflows I repeat multiple times, convert them into skills. Codex expands search...
Codex introduces a new feature that automatically analyzes user historical memory with a single prompt, extracts repetitive workflows, and converts them into evolvable skills, automating daily repetitive tasks.
Chronicle: A Multimodal Foundation Model for Joint Language and Time Series Understanding
Chronicle is a 324M-parameter decoder-only transformer pretrained from scratch on both natural language and time series, achieving competitive performance on NLU and time series classification tasks, and setting new state-of-the-art for frozen-embedding time series classification on UCR/UEA datasets.