Simon Willison
Aug 13
llm-gemini 0.33
Release: llm-gemini 0. 33 It's been a while since the last llm-gemini release.
Introducing ChatGPT Images 2.5
Simon Willison announces the release of ChatGPT Images 2.5, noting that OpenAI’s image generation models have processed over 3 billion images across ChatGPT Images and the GPT‑Image API. The new version improves instruction‑following across multiple turns, speeds up responses, and better preserves subjects from reference photos. Two new API model IDs—gpt‑image‑2.5‑sunburst and gpt‑image‑2.5‑flare—are available, with Sunburst recommended for precision editing and Flare for fast, high‑quality everyday generation. Willison has updated his openai_image.py CLI tool to accept reference images, demonstrating its use with a raccoon scientist prompt.
Related stories
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.
Simon Willison
Sep 5
Introducing GPT-6 Astra for developers
Simon Willison introduces GPT‑6 Astra, a new model that offers improved attention to detail, better prompt comprehension, and the ability to generate more sophisticated outputs. The model excels at creating 3D renderings, producing detailed scenes such as gardens, shipyards, animals, cityscapes, and even Dyson spheres. Willison highlights its whimsical creativity, noting examples like a pelican wearing a red neckerchief riding a bicycle.
Google AI Blog
Jan 31, 2024
MobileDiffusion: Rapid text-to-image generation on-device
Posted by Yang Zhao, Senior Software Engineer, and Tingbo Hou, Senior Staff Software Engineer, Core ML Text-to-image diffusion models have shown exceptional capabilities in generating high-quality images from text prompts. However, leading models feature billions of parameters and are consequently expensive to run, requiring powerful desktops or servers (e.
Simon Willison
Aug 24
llm-anthropic 0.27
The release of llm‑anthropic 0.27 updates the Anthropic plugin for LLM to be compatible with the newly released anthropic v1.0.0 Python library, which has switched from httpx to httpx2. This mirrors a similar change made by OpenAI in their v3.0.0 release two weeks prior. The update includes a migration guide and a pull request that ensures tests pass after upgrading to anthropic>=1.
Simon Willison
Sep 4
The Pelican comparison grid for Astra is pretty interesting
Simon Willison tested GPT‑6 Astra by generating SVG pelicans riding bicycles at various reasoning levels and compared the results to GPT‑5.6 Sol, Terra, and Luna. The Astra pelicans consistently outperformed the other models, especially at low and xhigh reasoning levels, and even the Astra max version produced high‑quality images. Astra also used fewer tokens and was roughly twice as expensive as Sol, yet its low‑level output was cheaper and superior to any Sol model.
Simon Willison
Sep 9
.blend URL Viewer
Simon Willison created a .blend URL Viewer tool that lets users view a Blender model of a Fabergé egg themed after the TV show Pluribus directly in their browser. He generated the egg image using ChatGPT Images 2.5, then fed it to GPT‑6 Astra with a custom Blender skill to produce several .blend files. The viewer, built with JavaScript, is now part of his tools collection for easy access to the resulting 3D model.
Google AI Blog
Mar 19, 2024
ScreenAI: A visual language model for UI and visually-situated language understanding
Posted by Srinivas Sunkara and Gilles Baechler, Software Engineers, Google Research Screen user interfaces (UIs) and infographics, such as charts, diagrams and tables, play important roles in human communication and human-machine interaction as they facilitate rich and interactive user experiences. UIs and infographics share similar design principles and visual language (e.
Simon Willison
Aug 31
Introducing wrapture
Introducing wrapture, a new Python library from Graham Dumpleton that extends the monkeypatching concepts of wrapt to support both testing and tracing simultaneously. It allows developers to wrap any function or method so that all accesses can be traced or overridden, serving as an alternative to unittest.mock and enabling observation of code without altering its behavior. Wrapture includes OpenTelemetry support and offers a configuration-based approach for adding tracing to existing projects, with the entire project and its documentation created under AI assistance.
Google AI Blog
Feb 23, 2024
VideoPrism: A foundational visual encoder for video understanding
Posted by Long Zhao, Senior Research Scientist, and Ting Liu, Senior Staff Software Engineer, Google Research An astounding number of videos are available on the Web, covering a variety of content from everyday moments people share to historical moments to scientific observations, each of which contains a unique record of the world. The right tools could help researchers analyze these videos, transforming how we understand the world around us.
OpenAI Blog
Mar 25, 2025
Introducing 4o Image Generation
At OpenAI, we have long believed image generation should be a primary capability of our language models. That’s why we’ve built our most advanced image generator yet into GPT‑4o.
arXiv Computation and Language
6d ago
ReFigBench: Benchmarking Scientific Figure Reconstruction as Editable PowerPoint Artifacts
ReFigBench is a benchmark that evaluates how well multimodal coding agents can transform scientific overview figures into editable PowerPoint slides, preserving text, layout, and document structure. The study uses 1,000 real figures from arXiv, testing agents from four model families across two workflows—direct code generation and a specialized PPTX workflow—within ten different harness configurations. Evaluation combines deterministic artifact checks, automated scoring by judges, and blinded human comparisons, revealing that workflow and harness choices significantly affect reconstruction quality and that even the best agents fall short of the ideal rubric.