Tag: prompts

Source URL: https://simonwillison.net/2025/Sep/23/why-ai-systems-might-never-be-secure/#atom-everything Source: Simon Willison’s Weblog Title: Why AI systems might never be secure Feedly Summary: Why AI systems might never be secure The Economist have a new piece out about LLM security, with this headline and subtitle: Why AI systems might never be secure A “lethal trifecta” of conditions opens them to abuse…

Simon Willison’s Weblog: Quoting Kate Niederhoffer, Gabriella Rosen Kellerman, Angela Lee, Alex Liebscher, Kristina Rapuano and Jeffrey T. Hancock

Sep 22, 2025

—

by

Source URL: https://simonwillison.net/2025/Sep/22/workslop/ Source: Simon Willison’s Weblog Title: Quoting Kate Niederhoffer, Gabriella Rosen Kellerman, Angela Lee, Alex Liebscher, Kristina Rapuano and Jeffrey T. Hancock Feedly Summary: We define workslop as AI generated work content that masquerades as good work, but lacks the substance to meaningfully advance a given task. Here’s how this happens. As AI…

Simon Willison’s Weblog: CompileBench: Can AI Compile 22-year-old Code?

Sep 22, 2025

—

by

Source URL: https://simonwillison.net/2025/Sep/22/compilebench/ Source: Simon Willison’s Weblog Title: CompileBench: Can AI Compile 22-year-old Code? Feedly Summary: CompileBench: Can AI Compile 22-year-old Code? Interesting new LLM benchmark from Piotr Grabowski and Piotr Migdał: how well can different models handle compilation challenges such as cross-compiling gucr for ARM64 architecture? This is one of my favorite applications of…

Simon Willison’s Weblog: Magistral 1.2

—

by

Source URL: https://simonwillison.net/2025/Sep/19/magistral/ Source: Simon Willison’s Weblog Title: Magistral 1.2 Feedly Summary: Mistral quietly released two new models yesterday: Magistral Small 1.2 (Apache 2.0, 96.1 GB on Hugging Face) and Magistral Medium 1.2 (not open weights same as Mistral’s other “medium" models.) Despite being described as "minor updates" to the Magistral 1.1 models these have…

Simon Willison’s Weblog: The Hidden Risk in Notion 3.0 AI Agents: Web Search Tool Abuse for Data Exfiltration

—

by

Source URL: https://simonwillison.net/2025/Sep/19/notion-lethal-trifecta/ Source: Simon Willison’s Weblog Title: The Hidden Risk in Notion 3.0 AI Agents: Web Search Tool Abuse for Data Exfiltration Feedly Summary: The Hidden Risk in Notion 3.0 AI Agents: Web Search Tool Abuse for Data Exfiltration Abi Raghuram reports that Notion 3.0, released yesterday, introduces new prompt injection data exfiltration vulnerabilities…

The Register: ChatGPT joins human league, now solves CAPTCHAs for the right prompt

—

by

Source URL: https://www.theregister.com/2025/09/19/how_to_trick_chatgpt_agents/ Source: The Register Title: ChatGPT joins human league, now solves CAPTCHAs for the right prompt Feedly Summary: Could this bot-prevention technique now be obsolete? ChatGPT can be tricked via cleverly worded prompts to violate its own policies and solve CAPTCHA puzzles, potentially making this human-proving security mechanism obsolete, researchers say.… AI Summary…

The Register: OpenAI plugs ShadowLeak bug in ChatGPT that let miscreants raid inboxes

—

by

Source URL: https://www.theregister.com/2025/09/19/openai_shadowleak_bug/ Source: The Register Title: OpenAI plugs ShadowLeak bug in ChatGPT that let miscreants raid inboxes Feedly Summary: Radware says flaw enabled hidden email prompts to trick Deep Research agent into exfiltrating sensitive data ChatGPT’s research assistant sprung a leak – since patched – that let attackers steal Gmail secrets with just a…

Slashdot: Gemini AI Solves Coding Problem That Stumped 139 Human Teams At ICPC World Finals

Sep 17, 2025

—

by

Source URL: https://slashdot.org/story/25/09/17/1923220/gemini-ai-solves-coding-problem-that-stumped-139-human-teams-at-icpc-world-finals?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: Gemini AI Solves Coding Problem That Stumped 139 Human Teams At ICPC World Finals Feedly Summary: AI Summary and Description: Yes Summary: Google’s generative AI model, Gemini 2.5, achieved a gold medal at the International Collegiate Programming Contest (ICPC), showcasing advancements towards artificial general intelligence. This performance highlights the…

Cloud Blog: How to secure your remote MCP server on Google Cloud

Sep 17, 2025

—

by