Experimental News Clipping Site

Tag: agent

  • Wired: Do Large Language Models Dream of AI Agents?

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.wired.com/story/sleeptime-compute-chatbots-memory/ Source: Wired Title: Do Large Language Models Dream of AI Agents? Feedly Summary: For AI models, knowing what to remember might be as important as knowing what to forget. Welcome to the era of “sleeptime compute.” AI Summary and Description: Yes Summary: The text introduces the concept of “sleeptime compute,” which emphasizes…

  • Embrace The Red: Amazon Q Developer for VS Code Vulnerable to Invisible Prompt Injection

    —

    by

    Kurt Seifried
    in

    Source URL: https://embracethered.com/blog/posts/2025/amazon-q-developer-interprets-hidden-instructions/ Source: Embrace The Red Title: Amazon Q Developer for VS Code Vulnerable to Invisible Prompt Injection Feedly Summary: The Amazon Q Developer VS Code Extension (Amazon Q) is a very popular coding agent, with over 1 million downloads. In previous posts we showed how prompt injection vulnerabilities in Amazon Q could lead…

  • Schneier on Security: Subverting AIOps Systems Through Poisoned Input Data

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.schneier.com/blog/archives/2025/08/subverting-aiops-systems-through-poisoned-input-data.html Source: Schneier on Security Title: Subverting AIOps Systems Through Poisoned Input Data Feedly Summary: In this input integrity attack against an AI system, researchers were able to fool AIOps tools: AIOps refers to the use of LLM-based agents to gather and analyze application telemetry, including system logs, performance metrics, traces, and alerts,…

  • The Register: KPMG wrote 100-page prompt to build agentic TaxBot

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/08/20/kpmg_giant_prompt_tax_agent/ Source: The Register Title: KPMG wrote 100-page prompt to build agentic TaxBot Feedly Summary: Produces advice in a single day instead of two weeks – without job losses The Australian arm of consultancy firm KPMG wrote a 100-page prompt to create an agentic system that prepares tax advice far faster than humans.……

  • Embrace The Red: Amazon Q Developer: Remote Code Execution with Prompt Injection

    —

    by

    Kurt Seifried
    in

    Source URL: https://embracethered.com/blog/posts/2025/amazon-q-developer-remote-code-execution/ Source: Embrace The Red Title: Amazon Q Developer: Remote Code Execution with Prompt Injection Feedly Summary: The Amazon Q Developer VS Code Extension (Amazon Q) is a popular coding agent, with over 1 million downloads. The extension is vulnerable to indirect prompt injection, and in this post we discuss a vulnerability that…

  • Docker: Building AI Agents with Docker MCP Toolkit: A Developer’s Real-World Setup

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.docker.com/blog/docker-mcp-ai-agent-developer-setup/ Source: Docker Title: Building AI Agents with Docker MCP Toolkit: A Developer’s Real-World Setup Feedly Summary: Building AI agents in the real world often involves more than just making model calls — it requires integrating with external tools, handling complex workflows, and ensuring the solution can scale in production. In this post,…

  • Embrace The Red: Amazon Q Developer: Secrets Leaked via DNS and Prompt Injection

    —

    by

    Kurt Seifried
    in

    Source URL: https://embracethered.com/blog/posts/2025/amazon-q-developer-data-exfil-via-dns/ Source: Embrace The Red Title: Amazon Q Developer: Secrets Leaked via DNS and Prompt Injection Feedly Summary: The next three posts will cover high severity vulnerabilities in the Amazon Q Developer VS Code Extension (Amazon Q), which is a very popular coding agent, with over 1 million downloads. It is vulnerable to…

  • Shabie’s blog: Agents are search over action space

    —

    by

    Kurt Seifried
    in

    Source URL: https://shabie.github.io/2025/08/18/agents-are-search-over-action-space.html Source: Shabie’s blog Title: Agents are search over action space Feedly Summary: It’s no secret that today’s LLM-based agents are unreliable. This makes them a gamble for most critical tasks, so where can they be safely applied? The answer lies in finding asymmetry: we should use them in domains where the downside…