Simon Willison

Codex bundles LibreOffice

Read the original on Simon Willison →

The OpenAI Codex desktop app (now ChatGPT) stores a 1.7 GB runtime bundle in the user’s ~/.cache directory. This bundle includes full installations of Python, Node.js, and native binaries for Poppler, git, and LibreOffice, along with plugins that enable Codex to locate and use these binaries. The presence of LibreOffice, a fork of OpenOffice.org, highlights the app’s reliance on open‑source office tools.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at Simon Willison.

Simon Willison
Aug 30

Understanding ChatGPT Work

OpenAI launched ChatGPT Work on July 9, offering two distinct products: Work Cloud, accessed via chatgpt.com or the mobile apps, and Work Local, available through the desktop app that can run programs on a user’s computer. Work Cloud is a paid‑only feature for $20/month and up subscribers, providing advanced capabilities such as code execution with internet access, a headless Chrome browser, and a persistent filesystem across sessions. The author notes that while ChatGPT Work claims to be better for tasks with clear outcomes, many users find the distinction unnecessary and prefer the standard Chat interface for most use cases.

Simon Willison
Aug 25

EVE Online: The Move to Python 3 Begins!

EVE Online is beginning its transition to Python 3, a move that will involve using the futurize script on 2.4 million lines of code and a manual review of about 20,000 differences between Python 2 and Python 3. The company has historically run on Stackless Python since 2003, with the last major upgrade in 2010 to Stackless Python 2.7. While the announcement does not detail how Stackless will be replaced, the team previously showcased a shift away from Stackless in their Carbon engine for EVE Frontier, leveraging the open‑source carbonengine/scheduler library.

Simon Willison
Sep 5

Using Blender with coding agents on macOS

Simon Willison demonstrates how to use Blender with coding agents on macOS by installing the full Mac application from blender.org and issuing prompts to ChatGPT Codex. He shows a step-by-step example where the agent renders a scene of a pelican riding a bicycle, then adds background flair and improves the image. The resulting image is generated via Blender's Python API.