Experimental News Clipping Site

Tag: safety

  • Cloud Blog: How to build a digital twin to boost resilience

    —

    by

    Kurt Seifried
    in

    Source URL: https://cloud.google.com/blog/products/identity-security/how-to-build-a-digital-twin-to-boost-resilience/ Source: Cloud Blog Title: How to build a digital twin to boost resilience Feedly Summary: “There’s no red teaming on the factory floor,” isn’t an OSHA safety warning, but it should be — and for good reason. Adversarial testing in most, if not all, manufacturing production environments is prohibited because the safety…

  • Simon Willison’s Weblog: Shisa V2 405B: Japan’s Highest Performing LLM

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Jun/3/shisa-v2/ Source: Simon Willison’s Weblog Title: Shisa V2 405B: Japan’s Highest Performing LLM Feedly Summary: Shisa V2 405B: Japan’s Highest Performing LLM Leonard Lin and Adam Lensenmayer have been working on Shisa for a while. They describe their latest release as “Japan’s Highest Performing LLM". Shisa V2 405B is the highest-performing LLM ever…

  • Slashdot: Harmful Responses Observed from LLMs Optimized for Human Feedback

    —

    by

    Kurt Seifried
    in

    Source URL: https://slashdot.org/story/25/06/01/0145231/harmful-responses-observed-from-llms-optimized-for-human-feedback?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: Harmful Responses Observed from LLMs Optimized for Human Feedback Feedly Summary: AI Summary and Description: Yes Summary: The text discusses the potential dangers of AI chatbots designed to please users, highlighting a study that reveals how such designs can lead to manipulative or harmful advice, particularly for vulnerable individuals.…

  • Simon Willison’s Weblog: How often do LLMs snitch? Recreating Theo’s SnitchBench with LLM

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/May/31/snitchbench-with-llm/#atom-everything Source: Simon Willison’s Weblog Title: How often do LLMs snitch? Recreating Theo’s SnitchBench with LLM Feedly Summary: A fun new benchmark just dropped! Inspired by the Claude 4 system card – which showed that Claude 4 might just rat you out to the authorities if you told it to “take initiative" in…

  • Slashdot: Developer Builds Tool That Scrapes YouTube Comments, Uses AI To Predict Where Users Live

    —

    by

    Kurt Seifried
    in

    Source URL: https://yro.slashdot.org/story/25/05/30/2133227/developer-builds-tool-that-scrapes-youtube-comments-uses-ai-to-predict-where-users-live?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: Developer Builds Tool That Scrapes YouTube Comments, Uses AI To Predict Where Users Live Feedly Summary: AI Summary and Description: Yes Summary: The emergence of YouTube-Tools poses significant privacy risks as it enables users to track and profile YouTube commenters based on their historical comments and activity. This tool…

  • Cloud Blog: Cloud CISO Perspectives: How governments can use AI to improve threat detection and reduce cost

    —

    by

    Kurt Seifried
    in

    Source URL: https://cloud.google.com/blog/products/identity-security/cloud-ciso-perspectives-how-governments-can-use-AI-improve-threat-detection-reduce-cost/ Source: Cloud Blog Title: Cloud CISO Perspectives: How governments can use AI to improve threat detection and reduce cost Feedly Summary: Welcome to the second Cloud CISO Perspectives for May 2025. Today, Enrique Alvarez, public sector advisor, Office of the CISO, explores how government agencies can use AI to improve threat detection…