Tag: Tags:

  • Simon Willison’s Weblog: Image segmentation using Gemini 2.5

    Source URL: https://simonwillison.net/2025/Apr/18/gemini-image-segmentation/ Source: Simon Willison’s Weblog Title: Image segmentation using Gemini 2.5 Feedly Summary: Max Woolf pointed out this new feature of the Gemini 2.5 series in a comment on Hacker News: One hidden note from Gemini 2.5 Flash when diving deep into the documentation: for image inputs, not only can the model be…

  • Simon Willison’s Weblog: MCP Run Python

    Source URL: https://simonwillison.net/2025/Apr/18/mcp-run-python/ Source: Simon Willison’s Weblog Title: MCP Run Python Feedly Summary: MCP Run Python Pydantic AI’s MCP server for running LLM-generated Python code in a sandbox. They ended up using a trick I explored two years ago: using a Deno process to run Pyodide in a WebAssembly sandbox. Here’s a bit of a…

  • Simon Willison’s Weblog: Start building with Gemini 2.5 Flash

    Source URL: https://simonwillison.net/2025/Apr/17/start-building-with-gemini-25-flash/ Source: Simon Willison’s Weblog Title: Start building with Gemini 2.5 Flash Feedly Summary: Start building with Gemini 2.5 Flash Google Gemini’s latest model is Gemini 2.5 Flash, available in (paid) preview as gemini-2.5-flash-preview-04-17. Building upon the popular foundation of 2.0 Flash, this new version delivers a major upgrade in reasoning capabilities, while…

  • Simon Willison’s Weblog: Quoting Ted Sanders, OpenAI

    Source URL: https://simonwillison.net/2025/Apr/17/ted-sanders/ Source: Simon Willison’s Weblog Title: Quoting Ted Sanders, OpenAI Feedly Summary: Our hypothesis is that o4-mini is a much better model, but we’ll wait to hear feedback from developers. Evals only tell part of the story, and we wouldn’t want to prematurely deprecate a model that developers continue to find value in.…

  • Simon Willison’s Weblog: Quoting James Betker

    Source URL: https://simonwillison.net/2025/Apr/16/james-betker/#atom-everything Source: Simon Willison’s Weblog Title: Quoting James Betker Feedly Summary: I work for OpenAI. […] o4-mini is actually a considerably better vision model than o3, despite the benchmarks. Similar to how o3-mini-high was a much better coding model than o1. I would recommend using o4-mini-high over o3 for any task involving vision.…

  • Simon Willison’s Weblog: Introducing OpenAI o3 and o4-mini

    Source URL: https://simonwillison.net/2025/Apr/16/introducing-openai-o3-and-o4-mini/ Source: Simon Willison’s Weblog Title: Introducing OpenAI o3 and o4-mini Feedly Summary: Introducing OpenAI o3 and o4-mini OpenAI are really emphasizing tool use with these: For the first time, our reasoning models can agentically use and combine every tool within ChatGPT—this includes searching the web, analyzing uploaded files and other data with…

  • Simon Willison’s Weblog: openai/codex

    Source URL: https://simonwillison.net/2025/Apr/16/openai-codex/ Source: Simon Willison’s Weblog Title: openai/codex Feedly Summary: openai/codex Just released by OpenAI, a “lightweight coding agent that runs in your terminal". Looks like their version of Claude Code. Tags: ai-assisted-programming, generative-ai, ai-agents, openai, ai, llms AI Summary and Description: Yes Summary: OpenAI’s recently released lightweight coding agent, integrated into the terminal,…

  • Simon Willison’s Weblog: GPT-4.1: Three new million token input models from OpenAI, including their cheapest model yet

    Source URL: https://simonwillison.net/2025/Apr/14/gpt-4-1/ Source: Simon Willison’s Weblog Title: GPT-4.1: Three new million token input models from OpenAI, including their cheapest model yet Feedly Summary: OpenAI introduced three new models this morning: GPT-4.1, GPT-4.1 mini and GPT-4.1 nano. These are API-only models right now, not available through the ChatGPT interface (though you can try them out…

  • Simon Willison’s Weblog: Note on 14th April 2025

    Source URL: https://simonwillison.net/2025/Apr/14/believe/ Source: Simon Willison’s Weblog Title: Note on 14th April 2025 Feedly Summary: Believing AI vendors who promise you that they won’t train on your data is a huge competitive advantage these days. Tags: llms, generative-ai, ai AI Summary and Description: Yes Summary: The assertion regarding AI vendors’ claims about not training on…