Experimental News Clipping Site

Tag: use

  • Simon Willison’s Weblog: Supabase MCP can leak your entire SQL database

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Jul/6/supabase-mcp-lethal-trifecta/#atom-everything Source: Simon Willison’s Weblog Title: Supabase MCP can leak your entire SQL database Feedly Summary: Supabase MCP can leak your entire SQL database Here’s yet another example of a lethal trifecta attack, where an LLM system combines access to private data, exposure to potentially malicious instructions and a mechanism to communicate data…

  • Slashdot: Two Sudo Vulnerabilities Discovered and Patched

    —

    by

    Kurt Seifried
    in

    Source URL: https://linux.slashdot.org/story/25/07/05/0323220/two-sudo-vulnerabilities-discovered-and-patched?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: Two Sudo Vulnerabilities Discovered and Patched Feedly Summary: AI Summary and Description: Yes Summary: The text discusses recently disclosed security vulnerabilities in Sudo that allow local attackers to escalate their privileges. Researchers have identified two critical flaws, CVE-2025-32462 and CVE-2025-32463, which could potentially expose systems to security risks and…

  • Slashdot: EU Sticks With Timeline For AI Rules

    —

    by

    Kurt Seifried
    in

    Source URL: https://slashdot.org/story/25/07/04/198257/eu-sticks-with-timeline-for-ai-rules?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: EU Sticks With Timeline For AI Rules Feedly Summary: AI Summary and Description: Yes Summary: The European Union is moving forward with its AI regulations despite calls from major tech companies for a delay. This situation has raised concerns among industry leaders about the impact of overlapping regulations on…

  • Slashdot: Simple Text Additions Can Fool Advanced AI Reasoning Models, Researchers Find

    —

    by

    Kurt Seifried
    in

    Source URL: https://tech.slashdot.org/story/25/07/04/1521245/simple-text-additions-can-fool-advanced-ai-reasoning-models-researchers-find Source: Slashdot Title: Simple Text Additions Can Fool Advanced AI Reasoning Models, Researchers Find Feedly Summary: AI Summary and Description: Yes Summary: The research highlights a significant vulnerability in state-of-the-art reasoning AI models through the “CatAttack” technique, which attaches irrelevant phrases to math problems, leading to higher error rates and inefficient responses.…

  • Simon Willison’s Weblog: awwaiid/gremllm

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Jul/4/gremllm/#atom-everything Source: Simon Willison’s Weblog Title: awwaiid/gremllm Feedly Summary: awwaiid/gremllm Delightfully cursed Python library by Brock Wilcox, built on top of LLM: from gremllm import Gremllm counter = Gremllm(“counter") counter.value = 5 counter.increment() print(counter.value) # 6? print(counter.to_roman_numerals()) # VI? You tell your Gremllm what it should be in the constructor, then it uses…

  • The Register: EU businesses want a pause on AI regulations so they can cope with unregulated Big Tech players

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/07/04/eu_businesses_push_for_freedom/ Source: The Register Title: EU businesses want a pause on AI regulations so they can cope with unregulated Big Tech players Feedly Summary: Mistral fears continental companies may not get time to escape ‘distant, behemoth corporations’ French AI business Mistral on Thursday announced an initiative called “AI for Citizens,” which it says…

  • The Register: AI models just don’t understand what they’re talking about

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/07/03/ai_models_potemkin_understanding/ Source: The Register Title: AI models just don’t understand what they’re talking about Feedly Summary: Researchers find models’ success at tests hides illusion of understanding Researchers from MIT, Harvard, and the University of Chicago have proposed the term “potemkin understanding" to describe a newly identified failure mode in large language models that…

  • Simon Willison’s Weblog: TIL: Rate limiting by IP using Cloudflare’s rate limiting rules

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Jul/3/rate-limiting-by-ip/#atom-everything Source: Simon Willison’s Weblog Title: TIL: Rate limiting by IP using Cloudflare’s rate limiting rules Feedly Summary: TIL: Rate limiting by IP using Cloudflare’s rate limiting rules My blog started timing out on some requests a few days ago, and it turned out there were misbehaving crawlers that were spidering my /search/…

  • Slashdot: ChatGPT Creates Phisher’s Paradise By Recommending the Wrong URLs for Major Companies

    —

    by

    Kurt Seifried
    in

    Source URL: https://it.slashdot.org/story/25/07/03/1912216/chatgpt-creates-phishers-paradise-by-recommending-the-wrong-urls-for-major-companies?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: ChatGPT Creates Phisher’s Paradise By Recommending the Wrong URLs for Major Companies Feedly Summary: AI Summary and Description: Yes Summary: The report highlights a flaw in the accuracy of AI-powered chatbots like GPT-4.1, which could create vulnerabilities for users and pose a security risk due to misinformation. This inaccuracy…