Experimental News Clipping Site

Tag: Context

  • 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: Microsoft Open Sources Copilot Chat for VS Code on GitHub

    —

    by

    Kurt Seifried
    in

    Source URL: https://developers.slashdot.org/story/25/07/05/1935203/microsoft-open-sources-copilot-chat-for-vs-code-on-github Source: Slashdot Title: Microsoft Open Sources Copilot Chat for VS Code on GitHub Feedly Summary: AI Summary and Description: Yes Summary: Microsoft has open-sourced the GitHub Copilot Chat extension for VS Code, allowing developers to access its internal workings, including data handling and telemetry. This transparency is significant for security, as it…

  • Slashdot: UK Minister Tells Turing AI Institute To Focus On Defense

    —

    by

    Kurt Seifried
    in

    Source URL: https://tech.slashdot.org/story/25/07/04/2011230/uk-minister-tells-turing-ai-institute-to-focus-on-defense Source: Slashdot Title: UK Minister Tells Turing AI Institute To Focus On Defense Feedly Summary: AI Summary and Description: Yes Summary: UK Science and Technology Secretary Peter Kyle emphasizes the importance of enhancing AI capabilities for national security, urging a shift in focus at the Alan Turing Institute towards defense. This reflects…

  • 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…

  • Simon Willison’s Weblog: Quoting Adam Gordon Bell

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Jul/3/adam-gordon-bell/#atom-everything Source: Simon Willison’s Weblog Title: Quoting Adam Gordon Bell Feedly Summary: I think that a lot of resistance to AI coding tools comes from the same place: fear of losing something that has defined you for so long. People are reacting against overblown hype, and there is overblown hype. I get that,…

  • 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/…

  • Docker: Docker Desktop 4.43: Expanded Model Runner, Reimagined MCP Catalog, MCP Server Submissions, and Smarter Gordon

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.docker.com/blog/docker-desktop-4-43/ Source: Docker Title: Docker Desktop 4.43: Expanded Model Runner, Reimagined MCP Catalog, MCP Server Submissions, and Smarter Gordon Feedly Summary: Docker Desktop 4.43 just rolled out a set of powerful updates that simplify how developers run, manage, and secure AI models and MCP tools.  Model Runner now includes better model management, expanded…

  • Simon Willison’s Weblog: Sandboxed tools in a loop

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Jul/3/sandboxed-tools-in-a-loop/#atom-everything Source: Simon Willison’s Weblog Title: Sandboxed tools in a loop Feedly Summary: Something I’ve realized about LLM tool use is that it means that if you can reduce a problem to something that can be solved by an LLM in a sandbox using tools in a loop, you can brute force that…

  • The Register: Tariffs and trade turmoil driving up cost and build times for datacenters

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/07/03/tariffs_and_trade_turmoil_driving/ Source: The Register Title: Tariffs and trade turmoil driving up cost and build times for datacenters Feedly Summary: Biz needs AI infra for training ever larger models, but something’s gotta give World War Fee Datacenter operators in Northern Europe say US tariffs and growing global geopolitical instability are inflating costs and causing…