Experimental News Clipping Site

Tag: Aria

  • Schneier on Security: “Emergent Misalignment” in LLMs

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.schneier.com/blog/archives/2025/02/emergent-misalignment-in-llms.html Source: Schneier on Security Title: “Emergent Misalignment” in LLMs Feedly Summary: Interesting research: “Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs“: Abstract: We present a surprising result regarding LLMs and alignment. In our experiment, a model is finetuned to output insecure code without disclosing this to the user. The resulting model…

  • Slashdot: US Intelligence Chief Opposes UK Order for Apple Encryption Backdoor

    —

    by

    Kurt Seifried
    in

    Source URL: https://news.slashdot.org/story/25/02/26/187252/us-intelligence-chief-opposes-uk-order-for-apple-encryption-backdoor?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: US Intelligence Chief Opposes UK Order for Apple Encryption Backdoor Feedly Summary: AI Summary and Description: Yes Summary: The text discusses a significant legal and privacy issue involving a British order that requires Apple to compromise its encryption, potentially infringing on American rights and privacy. U.S. Director of National…

  • Unit 42: RustDoor and Koi Stealer for macOS Used by North Korea-Linked Threat Actor to Target the Cryptocurrency Sector

    —

    by

    Kurt Seifried
    in

    Source URL: https://unit42.paloaltonetworks.com/?p=138378 Source: Unit 42 Title: RustDoor and Koi Stealer for macOS Used by North Korea-Linked Threat Actor to Target the Cryptocurrency Sector Feedly Summary: Koi Stealer and RustDoor malware were used in a campaign linked to North Korea. This activity targeted crypto wallet owners. The post RustDoor and Koi Stealer for macOS Used…

  • Hacker News: Evaluating modular RAG with reasoning models

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.kapa.ai/blog/evaluating-modular-rag-with-reasoning-models Source: Hacker News Title: Evaluating modular RAG with reasoning models Feedly Summary: Comments AI Summary and Description: Yes Summary: The text outlines the challenges and potential of Modular Retrieval-Augmented Generation (RAG) systems using reasoning models like o3-mini. It emphasizes the distinction between reasoning capabilities and practical experience in tool usage, highlighting insights…

  • Simon Willison’s Weblog: olmOCR

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Feb/26/olmocr/#atom-everything Source: Simon Willison’s Weblog Title: olmOCR Feedly Summary: olmOCR New from Ai2 – olmOCR is “an open-source tool designed for high-throughput conversion of PDFs and other documents into plain text while preserving natural reading order". At its core is allenai/olmOCR-7B-0225-preview, a Qwen2-VL-7B-Instruct variant trained on ~250,000 pages of diverse PDF content (both…

  • The Register: Malware variants that target operational tech systems are very rare – but 2 were found last year

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/02/25/new_ics_malware_dragos/ Source: The Register Title: Malware variants that target operational tech systems are very rare – but 2 were found last year Feedly Summary: Fuxnet and FrostyGoop were both used in the Russia-Ukraine war Two new malware variants specifically designed to disrupt critical industrial processes were set loose on operational technology networks last…

  • The Register: How nice that state-of-the-art LLMs reveal their reasoning … for miscreants to exploit

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/02/25/chain_of_thought_jailbreaking/ Source: The Register Title: How nice that state-of-the-art LLMs reveal their reasoning … for miscreants to exploit Feedly Summary: Blueprints shared for jail-breaking models that expose their chain-of-thought process Analysis AI models like OpenAI o1/o3, DeepSeek-R1, and Gemini 2.0 Flash Thinking can mimic human reasoning through a process called chain of thought.……

  • Unit 42: Auto-Color: An Emerging and Evasive Linux Backdoor

    —

    by

    Kurt Seifried
    in

    Source URL: https://unit42.paloaltonetworks.com/?p=138356 Source: Unit 42 Title: Auto-Color: An Emerging and Evasive Linux Backdoor Feedly Summary: The new Linux malware named Auto-color uses advanced evasion tactics. Discovered by Unit 42, this article cover its installation, evasion features and more. The post Auto-Color: An Emerging and Evasive Linux Backdoor appeared first on Unit 42. AI Summary…

  • 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…