Tags: simon willison*

0 bookmark(s) - Sort by: Date ↓ / Title /

  1. Alibaba's Qwen 2.5 LLM now supports input token limits up to 1 million using Dual Chunk Attention. Two models are released on Hugging Face, requiring significant VRAM for full capacity. Challenges in deployment with quantized GGUF versions and system resource constraints are discussed.

  2. Simon Willison shares his predictions regarding the development of AI and LLMs over the next 1, 3, and 6 years. He discusses the potential failure of AI agents to fully realize their expected capabilities, the success of coding and research assistants, a Pulitzer prize for AI-assisted investigative reporting within three years, the emergence of privacy laws, the creation of amazing art in six years, and concerns about AGI/ASI leading to mass civil unrest.

    2025-01-10 Tags: , , , by klotz
  3. A review of advancements and key themes in Large Language Models over the course of 2024, including GPT-4 barrier breaking, reduced costs, multimodal capabilities, and more.

    2025-01-01 Tags: , , by klotz
  4. Concatenate a directory full of files into a single prompt for use with LLMs

    2024-12-12 Tags: , , , by klotz
  5. Simon Willison reviews the new Qwen2.5-Coder-32B, an open-source LLM by Alibaba, which performs well on various coding benchmarks and can run on personal devices like his MacBook Pro M2.

  6. LLM 0.17 release enables multi-modal input, allowing users to send images, audio, and video files to Large Language Models like GPT-4o, Llama, and Gemini, with a Python API and cost-effective pricing.

    2024-10-29 Tags: , , , , , , , , by klotz
  7. A new plugin for LLM, llm-jq, generates and executes jq programs based on human-language descriptions, allowing users to manipulate JSON data without needing to write jq syntax.

    2024-10-28 Tags: , , , , by klotz
  8. Simon Willison explains how to use the mistral.rs library in Rust to run the Llama Vision model on a Mac M2 laptop. He provides a detailed example and discusses the memory usage and GPU utilization.

  9. The author records a screen capture of their Gmail account and uses Google Gemini to extract numeric values from the video.

  10. Datasette is introduced as a functional interactive frontend to tabulated data, either in CSV format or a database schema, catering to data journalists, museum curators, archivists, local governments, and researchers.

    The author explores creating tables and inserting data into a SQLite database, then targets the database with Datasette to showcase how errors in data can be identified and corrected.

Top of the page

First / Previous / Next / Last / Page 1 of 0 SemanticScuttle - klotz.me: tagged with "simon willison"

About - Propulsed by SemanticScuttle