Experimental News Clipping Site

Tag: Simon Willison

  • Simon Willison’s Weblog: Defeating Nondeterminism in LLM Inference

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Sep/11/defeating-nondeterminism/#atom-everything Source: Simon Willison’s Weblog Title: Defeating Nondeterminism in LLM Inference Feedly Summary: Defeating Nondeterminism in LLM Inference A very common question I see about LLMs concerns why they can’t be made to deliver the same response to the same prompt by setting a fixed random number seed. Like many others I had…

  • Simon Willison’s Weblog: Claude API: Web fetch tool

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Sep/10/claude-web-fetch-tool/#atom-everything Source: Simon Willison’s Weblog Title: Claude API: Web fetch tool Feedly Summary: Claude API: Web fetch tool New in the Claude API: if you pass the web-fetch-2025-09-10 beta header you can add {“type": "web_fetch_20250910", "name": "web_fetch", "max_uses": 5} to your "tools" list and Claude will gain the ability to fetch content from…

  • Simon Willison’s Weblog: Recreating the Apollo AI adoption rate chart with GPT-5, Python and Pyodide

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Sep/9/apollo-ai-adoption/#atom-everything Source: Simon Willison’s Weblog Title: Recreating the Apollo AI adoption rate chart with GPT-5, Python and Pyodide Feedly Summary: Apollo Global Management’s “Chief Economist" Dr. Torsten Sløk released this interesting chart which appears to show a slowdown in AI adoption rates among large (>250 empoloyees) companies: Here’s the full description that accompanied…

  • Simon Willison’s Weblog: Anthropic status: Model output quality

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Sep/9/anthropic-model-output-quality/ Source: Simon Willison’s Weblog Title: Anthropic status: Model output quality Feedly Summary: Anthropic status: Model output quality Anthropic previously reported model serving bugs that affected Claude Opus 4 and 4.1 for 56.5 hours. They’ve now fixed additional bugs affecting “a small percentage" of Sonnet 4 requests for almost a month, plus a…

  • Simon Willison’s Weblog: Load Llama-3.2 WebGPU in your browser from a local folder

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Sep/8/webgpu-local-folder/#atom-everything Source: Simon Willison’s Weblog Title: Load Llama-3.2 WebGPU in your browser from a local folder Feedly Summary: Load Llama-3.2 WebGPU in your browser from a local folder Inspired by a comment on Hacker News I decided to see if it was possible to modify the transformers.js-examples/tree/main/llama-3.2-webgpu Llama 3.2 chat demo (online here,…

  • Simon Willison’s Weblog: Quoting James Luan

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Sep/8/james-luan/ Source: Simon Willison’s Weblog Title: Quoting James Luan Feedly Summary: I recently spoke with the CTO of a popular AI note-taking app who told me something surprising: they spend twice as much on vector search as they do on OpenAI API calls. Think about that for a second. Running the retrieval layer…

  • Simon Willison’s Weblog: Is the LLM response wrong, or have you just failed to iterate it?

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Sep/7/is-the-llm-response-wrong-or-have-you-just-failed-to-iterate-it/#atom-everything Source: Simon Willison’s Weblog Title: Is the LLM response wrong, or have you just failed to iterate it? Feedly Summary: Is the LLM response wrong, or have you just failed to iterate it? More from Mike Caulfield (see also the SIFT method). He starts with a fantastic example of Google’s AI mode…

  • Simon Willison’s Weblog: Quoting Jason Liu

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Sep/6/jason-liu/#atom-everything Source: Simon Willison’s Weblog Title: Quoting Jason Liu Feedly Summary: I am once again shocked at how much better image retrieval performance you can get if you embed highly opinionated summaries of an image, a summary that came out of a visual language model, than using CLIP embeddings themselves. If you tell…