Article · Simon Willison ·

Quoting Ted Sanders

Simon Willison

In general, LLM performance is incredibly multidimensional. There's no guarantee of a fixed ordering where the model that is best at math is also the model that's best at jokes. Despite that complexity, much of the variation in performance is explained by just a single variable: model size.

Read at simonwillison.net The opening of the original, or for stories before 30 October 2026 an AI model's summary of it. Check the original before you rely on a detail.

More from Simon Willison

All stories
Simon Willison

ArticleSimon Willison

API credits benefit for eligible ChatGPT subscriptions

OpenAI has launched an API credits benefit for eligible ChatGPT subscriptions, mirroring a similar benefit Anthropic announced earlier for its Max and Team plans. OpenAI subscribers to its $100, $200, or $500 per month plans now receive the equivalent quantity of expiring credits to apply to one of their API organizations.

Simon Willison

ArticleSimon Willison

Building a multiplayer game world with autonomous Fable-class models

Simon Willison's blog post shares a piece by Jacob Sansbury describing how his company is building Spawn, a massively multiplayer gaming environment in which players use prompts to an in-game agent called Savi to modify the game world. Willison reports trying it on his phone and being able to prompt a castle into existence, then a dragon, then ride the dragon around the castle, calling the work an exploration of the bleeding edge of agentic engineering against frontier models.

Simon Willison

ArticleSimon Willison

Quoting Ben Hylak

Ben Hylak is quoted saying that every product he uses should be a headless MCP that feeds into an agent, so he never has to think about anything underneath, except his own product, which keeps a UI that customers love.