Experimental News Clipping Site

Tag: instruction

  • Embrace The Red: Sneaking Invisible Instructions by Developers in Windsurf

    —

    by

    Kurt Seifried
    in

    Source URL: https://embracethered.com/blog/posts/2025/windsurf-sneaking-invisible-instructions-for-prompt-injection/ Source: Embrace The Red Title: Sneaking Invisible Instructions by Developers in Windsurf Feedly Summary: Imagine a malicious instruction hidden in plain sight, invisible to you but not to the AI. This is a vulnerability discovered in Windsurf Cascade, it follows invisible instructions. This means there can be instructions in a file or…

  • Cloud Blog: How startups can help build — and benefit from — the AI revolution

    —

    by

    Kurt Seifried
    in

    Source URL: https://cloud.google.com/blog/products/ai-machine-learning/industry-leaders-on-whats-next-for-startups-and-ai/ Source: Cloud Blog Title: How startups can help build — and benefit from — the AI revolution Feedly Summary: Startups are at the forefront of generative AI development, pushing current capabilities and unlocking new potential. Building on our Future of AI: Perspectives for Startups 2025 report, several of the AI industry leaders…

  • Cloud Blog: How to build a real-time voice agent with Gemini, Google ADK, and A2A protocol

    —

    by

    Kurt Seifried
    in

    Source URL: https://cloud.google.com/blog/products/ai-machine-learning/build-a-real-time-voice-agent-with-gemini-adk/ Source: Cloud Blog Title: How to build a real-time voice agent with Gemini, Google ADK, and A2A protocol Feedly Summary: Building advanced conversational AI has moved well beyond text. Now, we can use AI to create real-time, voice-driven agents. However, these systems need low-latency, two-way communication, real-time information retrieval, and the ability…

  • The Register: Perplexity’s Comet browser naively processed pages with evil instructions

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/08/20/perplexity_comet_browser_prompt_injection/ Source: The Register Title: Perplexity’s Comet browser naively processed pages with evil instructions Feedly Summary: Rival Brave flags prompt injection vulnerability, now patched To the surprise of no one in the security industry, processing untrusted, unvalidated input is a bad idea.… AI Summary and Description: Yes Summary: The text discusses a recently…

  • 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…

  • Simon Willison’s Weblog: llama.cpp guide: running gpt-oss with llama.cpp

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Aug/19/gpt-oss-with-llama-cpp/ Source: Simon Willison’s Weblog Title: llama.cpp guide: running gpt-oss with llama.cpp Feedly Summary: llama.cpp guide: running gpt-oss with llama.cpp Really useful official guide to running the OpenAI gpt-oss models using llama-server from llama.cpp – which provides an OpenAI-compatible localhost API and a neat web interface for interacting with the models. TLDR version…

  • Slashdot: LLM Found Transmitting Behavioral Traits to ‘Student’ LLM Via Hidden Signals in Data

    —

    by

    Kurt Seifried
    in

    Source URL: https://slashdot.org/story/25/08/17/0331217/llm-found-transmitting-behavioral-traits-to-student-llm-via-hidden-signals-in-data?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: LLM Found Transmitting Behavioral Traits to ‘Student’ LLM Via Hidden Signals in Data Feedly Summary: AI Summary and Description: Yes Summary: The study highlights a concerning phenomenon in AI development known as subliminal learning, where a “teacher” model instills traits in a “student” model without explicit instruction. This can…