Simon Willison’s Weblog
1 day ago · To test this system, we pointed it at an ambitious goal: building a web browser from scratch. The agents ran for close to a week, writing over 1 million lines of code across 1,000 files. You can …
Cursor's recent experiment involved running hundreds of AI ...
8 hours ago · Cursor's recent experiment involved running hundreds of AI agents for nearly a week to build a web browser, writing 1M+ lines of code across 1,000 files — They ended up running planners …
Cursor's recent experiment involved running hundreds of AI ...
8 hours ago · Simon Willison / Simon Willison's Weblog: Cursor's recent experiment involved running hundreds of AI agents for nearly a week to build a web browser, writing 1M+ lines of code across …
Gemini 3 Pro is priced at $2-$4 per 1M input tokens and $12 ...
Simon Willison / Simon Willison's Weblog: Gemini 3 Pro is priced at $2-$4 per 1M input tokens and $12-$18 per 1M output tokens, cheaper than Claude Sonnet 4.5 but more expensive than GPT-5.1 — …
Claude Sonnet 4 Now Supports 1M Tokens of Context
Aug 25, 2025 · Claude Sonnet 4 now supports 1M tokens of context. Gemini and OpenAI both have million token models, so it’s good to see Anthropic catching up. This is 5x the previous 200,000 …
Willison: The killer app of Gemini Pro 1.5 is video — cto4.ai
Feb 22, 2024 · Simon Willison tries out Gemini Pro 1.5 on video, and suggests its 1M token context size opens up powerful new opportunities using video prompts.
Gemini 2.5 Pro hands-on: a very strong model with 1M input ...
Gemini 2.5 Pro hands-on: a very strong model with 1M input and 64K output tokens, a January 2025 knowledge cut-off, and very, very impressive coding skills — There's a new release from Google …