Experimental News Clipping Site

Tag: Tags:

  • Simon Willison’s Weblog: Cross-Agent Privilege Escalation: When Agents Free Each Other

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Sep/24/cross-agent-privilege-escalation/ Source: Simon Willison’s Weblog Title: Cross-Agent Privilege Escalation: When Agents Free Each Other Feedly Summary: Cross-Agent Privilege Escalation: When Agents Free Each Other Here’s a clever new form of AI exploit from Johann Rehberger, who has coined the term Cross-Agent Privilege Escalation to describe an attack where multiple coding agents – GitHub…

  • Simon Willison’s Weblog: GPT-5-Codex

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Sep/23/gpt-5-codex/#atom-everything Source: Simon Willison’s Weblog Title: GPT-5-Codex Feedly Summary: GPT-5-Codex OpenAI half-relased this model earlier this month, adding it to their Codex CLI tool but not their API. Today they’ve fixed that – the new model can now be accessed as gpt-5-codex. It’s priced the same as regular GPT-5: $1.25/million input tokens, $10/million…

  • Simon Willison’s Weblog: Qwen3-VL: Sharper Vision, Deeper Thought, Broader Action

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Sep/23/qwen3-vl/ Source: Simon Willison’s Weblog Title: Qwen3-VL: Sharper Vision, Deeper Thought, Broader Action Feedly Summary: Qwen3-VL: Sharper Vision, Deeper Thought, Broader Action I’ve been looking forward to this. Qwen 2.5 VL is one of the best available open weight vision LLMs, so I had high hopes for Qwen 3’s vision models. Firstly, we…

  • Simon Willison’s Weblog: Why AI systems might never be secure

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Sep/23/why-ai-systems-might-never-be-secure/#atom-everything Source: Simon Willison’s Weblog Title: Why AI systems might never be secure Feedly Summary: Why AI systems might never be secure The Economist have a new piece out about LLM security, with this headline and subtitle: Why AI systems might never be secure A “lethal trifecta” of conditions opens them to abuse…

  • Simon Willison’s Weblog: Quoting Kate Niederhoffer, Gabriella Rosen Kellerman, Angela Lee, Alex Liebscher, Kristina Rapuano and Jeffrey T. Hancock

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Sep/22/workslop/ Source: Simon Willison’s Weblog Title: Quoting Kate Niederhoffer, Gabriella Rosen Kellerman, Angela Lee, Alex Liebscher, Kristina Rapuano and Jeffrey T. Hancock Feedly Summary: We define workslop as AI generated work content that masquerades as good work, but lacks the substance to meaningfully advance a given task. Here’s how this happens. As AI…

  • Simon Willison’s Weblog: Four new releases from Qwen

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Sep/22/qwen/ Source: Simon Willison’s Weblog Title: Four new releases from Qwen Feedly Summary: It’s been an extremely busy day for team Qwen. Within the last 24 hours (all links to Twitter, which seems to be their preferred platform for these announcements): Qwen3-Next-80B-A3B-Instruct-FP8 and Qwen3-Next-80B-A3B-Thinking-FP8 – official FP8 quantized versions of their Qwen3-Next models.…

  • Simon Willison’s Weblog: CompileBench: Can AI Compile 22-year-old Code?

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Sep/22/compilebench/ Source: Simon Willison’s Weblog Title: CompileBench: Can AI Compile 22-year-old Code? Feedly Summary: CompileBench: Can AI Compile 22-year-old Code? Interesting new LLM benchmark from Piotr Grabowski and Piotr Migdał: how well can different models handle compilation challenges such as cross-compiling gucr for ARM64 architecture? This is one of my favorite applications of…

  • Simon Willison’s Weblog: Locally AI

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Sep/21/locally-ai/ Source: Simon Willison’s Weblog Title: Locally AI Feedly Summary: Locally AI Handy new iOS app by Adrien Grondin for running local LLMs on your phone. It just added support for the new iOS 26 Apple Foundation model, so you can install this app and instantly start a conversation with that model without…

  • Simon Willison’s Weblog: Grok 4 Fast

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Sep/20/grok-4-fast/ Source: Simon Willison’s Weblog Title: Grok 4 Fast Feedly Summary: Grok 4 Fast New hosted reasoning model from xAI that’s designed to be fast and extremely competitive on price. It has a 2 million token context window and “was trained end-to-end with tool-use reinforcement learning". It’s priced at $0.20/million input tokens and…

  • Simon Willison’s Weblog: httpjail

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Sep/19/httpjail/#atom-everything Source: Simon Willison’s Weblog Title: httpjail Feedly Summary: httpjail Here’s a promising new (experimental) project in the sandboxing space from Ammar Bandukwala at Coder. httpjail provides a Rust CLI tool for running an individual process against a custom configured HTTP proxy. The initial goal is to help run coding agents like Claude…