Experimental News Clipping Site

Tag: JavaScript

  • Simon Willison’s Weblog: Large Language Models can run tools in your terminal with LLM 0.26

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/May/27/llm-tools/ Source: Simon Willison’s Weblog Title: Large Language Models can run tools in your terminal with LLM 0.26 Feedly Summary: LLM 0.26 is out with the biggest new feature since I started the project: support for tools. You can now use the LLM CLI tool – and Python library – to grant LLMs…

  • Slashdot: Destructive Malware Available In NPM Repo Went Unnoticed For 2 Years

    —

    by

    Kurt Seifried
    in

    Source URL: https://yro.slashdot.org/story/25/05/22/2012209/destructive-malware-available-in-npm-repo-went-unnoticed-for-2-years?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: Destructive Malware Available In NPM Repo Went Unnoticed For 2 Years Feedly Summary: AI Summary and Description: Yes Summary: The text highlights a significant security threat found in open-source software archives, where malicious packages imitating legitimate ones have been identified. This incident underscores the risks associated with software supply…

  • Simon Willison’s Weblog: Gemini Diffusion

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/May/21/gemini-diffusion/ Source: Simon Willison’s Weblog Title: Gemini Diffusion Feedly Summary: Gemini Diffusion Another of the announcements from Google I/O yesterday was Gemini Diffusion, Google’s first LLM to use diffusion (similar to image models like Imagen and Stable Diffusion) in place of transformers. Google describe it like this: Traditional autoregressive language models generate text…

  • Microsoft Security Blog: Lumma Stealer: Breaking down the delivery techniques and capabilities of a prolific infostealer

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.microsoft.com/en-us/security/blog/2025/05/21/lumma-stealer-breaking-down-the-delivery-techniques-and-capabilities-of-a-prolific-infostealer/ Source: Microsoft Security Blog Title: Lumma Stealer: Breaking down the delivery techniques and capabilities of a prolific infostealer Feedly Summary: Over the past year, Microsoft Threat Intelligence observed the persistent growth and operational sophistication of Lumma Stealer, an info-stealing malware used by multiple financially motivated threat actors to target various industries. Microsoft,…

  • The Register: Freshly discovered bug in OpenPGP.js undermines whole point of encrypted comms

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/05/20/openpgp_js_flaw/ Source: The Register Title: Freshly discovered bug in OpenPGP.js undermines whole point of encrypted comms Feedly Summary: Update before that proof-of-concept comes to bite Security researchers are sounding the alarm over a fresh flaw in the JavaScript implementation of OpenPGP (OpenPGP.js) that allows both signed and encrypted messages to be spoofed.… AI…

  • Slashdot: Over 3,200 Cursor Users Infected by Malicious Credential-Stealing npm Packages

    —

    by

    Kurt Seifried
    in

    Source URL: https://developers.slashdot.org/story/25/05/11/2222257/over-3200-cursor-users-infected-by-malicious-credential-stealing-npm-packages?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: Over 3,200 Cursor Users Infected by Malicious Credential-Stealing npm Packages Feedly Summary: AI Summary and Description: Yes Summary: The text highlights a recent cybersecurity threat involving malicious npm (Node Package Manager) packages that target the AI-powered code-editing tool Cursor on macOS. The packages are designed to steal user credentials…

  • Simon Willison’s Weblog: Qwen3-8B

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/May/2/qwen3-8b/#atom-everything Source: Simon Willison’s Weblog Title: Qwen3-8B Feedly Summary: Having tried a few of the Qwen 3 models now my favorite is a bit of a surprise to me: I’m really enjoying Qwen3-8B. I’ve been running prompts through the MLX 4bit quantized version, mlx-community/Qwen3-8B-4bit. I’m using llm-mlx like this: llm install llm-mlx llm…