Experimental News Clipping Site

Tag: AI security

  • Hacker News: Grok 3 is highly vulnerable to indirect prompt injection

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Feb/23/grok-3-indirect-prompt-injection/ Source: Hacker News Title: Grok 3 is highly vulnerable to indirect prompt injection Feedly Summary: Comments AI Summary and Description: Yes Summary: The text highlights significant vulnerabilities in xAI’s Grok 3 related to indirect prompt injection attacks, especially in the context of its operation on Twitter (X). This raises critical security concerns…

  • Schneier on Security: More Research Showing AI Breaking the Rules

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.schneier.com/blog/archives/2025/02/more-research-showing-ai-breaking-the-rules.html Source: Schneier on Security Title: More Research Showing AI Breaking the Rules Feedly Summary: These researchers had LLMs play chess against better opponents. When they couldn’t win, they sometimes resorted to cheating. Researchers gave the models a seemingly impossible task: to win against Stockfish, which is one of the strongest chess engines…

  • The Register: Rather than add a backdoor, Apple decides to kill iCloud E2EE for UK peeps

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/02/24/rather_than_add_a_backdoor/ Source: The Register Title: Rather than add a backdoor, Apple decides to kill iCloud E2EE for UK peeps Feedly Summary: PLUS: SEC launches new crypto crime unit; Phishing toolkit upgraded; and more Infosec in brief Apple has responded to the UK government’s demand for access to its customers’ data stored in iCloud…

  • Simon Willison’s Weblog: Grok 3 is highly vulnerable to indirect prompt injection

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Feb/23/grok-3-indirect-prompt-injection/#atom-everything Source: Simon Willison’s Weblog Title: Grok 3 is highly vulnerable to indirect prompt injection Feedly Summary: Grok 3 is highly vulnerable to indirect prompt injection xAI’s new Grok 3 is so far exclusively deployed on Twitter (aka “X"), and apparently uses its ability to search for relevant tweets as part of every…

  • Hacker News: AI CUDA Engineer: Agentic CUDA Kernel Discovery, Optimization and Composition

    —

    by

    Kurt Seifried
    in

    Source URL: https://sakana.ai/ai-cuda-engineer/ Source: Hacker News Title: AI CUDA Engineer: Agentic CUDA Kernel Discovery, Optimization and Composition Feedly Summary: Comments AI Summary and Description: Yes **Summary:** The text discusses significant advancements made by Sakana AI in automating the creation and optimization of AI models, particularly through the development of The AI CUDA Engineer, which leverages…

  • Hacker News: Protoclone, the first bipedal, musculoskeletal Android

    —

    by

    Kurt Seifried
    in

    Source URL: https://clonerobotics.com/android Source: Hacker News Title: Protoclone, the first bipedal, musculoskeletal Android Feedly Summary: Comments AI Summary and Description: Yes Summary: The text discusses the emergence of natural language interfaces, particularly highlighting the evolution represented by the Clone Alpha, which leverages large language models (LLMs) to facilitate communication in plain English. This development signifies…

  • Simon Willison’s Weblog: My LLM codegen workflow atm

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Feb/21/my-llm-codegen-workflow-atm/#atom-everything Source: Simon Willison’s Weblog Title: My LLM codegen workflow atm Feedly Summary: My LLM codegen workflow atm Harper Reed describes his workflow for writing code with the assistance of LLMs. This is clearly a very well-thought out process, which has evolved a lot already and continues to change. Harper starts greenfield projects…

  • Slashdot: DeepSeek To Share Some AI Model Code

    —

    by

    Kurt Seifried
    in

    Source URL: https://news.slashdot.org/story/25/02/21/1842227/deepseek-to-share-some-ai-model-code?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: DeepSeek To Share Some AI Model Code Feedly Summary: AI Summary and Description: Yes Summary: DeepSeek, a Chinese startup, has announced its commitment to open-source AI by making several code repositories publicly available. This initiative signals a significant contribution to the field, potentially impacting the competitive landscape in AI…

  • Hacker News: SWE-Bench tainted by answer leakage; real pass rates significantly lower

    —

    by

    Kurt Seifried
    in

    Source URL: https://arxiv.org/abs/2410.06992 Source: Hacker News Title: SWE-Bench tainted by answer leakage; real pass rates significantly lower Feedly Summary: Comments AI Summary and Description: Yes Summary: The paper “SWE-Bench+: Enhanced Coding Benchmark for LLMs” addresses significant data quality issues in the evaluation of Large Language Models (LLMs) for coding tasks. It presents empirical analysis revealing…

  • Schneier on Security: Implementing Cryptography in AI Systems

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.schneier.com/blog/archives/2025/02/implementing-cryptography-in-ai-systems.html Source: Schneier on Security Title: Implementing Cryptography in AI Systems Feedly Summary: Interesting research: “How to Securely Implement Cryptography in Deep Neural Networks.” Abstract: The wide adoption of deep neural networks (DNNs) raises the question of how can we equip them with a desired cryptographic functionality (e.g, to decrypt an encrypted input,…