Experimental News Clipping Site

Tag: prompt

  • Cisco Talos Blog: Great Scott, I’m tired

    —

    by

    Kurt Seifried
    in

    Source URL: https://blog.talosintelligence.com/great-scott-im-tired/ Source: Cisco Talos Blog Title: Great Scott, I’m tired Feedly Summary: Hazel celebrates unseen effort in cybersecurity and shares some PII. Completely unrelated, but did you know “Back to the Future” turns 40 this year? AI Summary and Description: Yes Summary: The content primarily discusses recent cybersecurity threats, including the emergence of…

  • Slashdot: OpenAI Says GPT-5 Stacks Up To Humans in a Wide Range of Jobs

    —

    by

    Kurt Seifried
    in

    Source URL: https://slashdot.org/story/25/09/25/176219/openai-says-gpt-5-stacks-up-to-humans-in-a-wide-range-of-jobs?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: OpenAI Says GPT-5 Stacks Up To Humans in a Wide Range of Jobs Feedly Summary: AI Summary and Description: Yes Summary: OpenAI has introduced GDPval, a new benchmark to assess the performance of its AI models against that of human professionals across various industries. The benchmark indicates that models…

  • Docker: Run, Test, and Evaluate Models and MCP Locally with Docker + Promptfoo

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.docker.com/blog/evaluate-models-and-mcp-with-promptfoo-docker/ Source: Docker Title: Run, Test, and Evaluate Models and MCP Locally with Docker + Promptfoo Feedly Summary: Promptfoo is an open-source CLI and library for evaluating LLM apps. Docker Model Runner makes it easy to manage, run, and deploy AI models using Docker. The Docker MCP Toolkit is a local gateway that…

  • Simon Willison’s Weblog: Cross-Agent Privilege Escalation: When Agents Free Each Other

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Sep/24/cross-agent-privilege-escalation/ Source: Simon Willison’s Weblog Title: Cross-Agent Privilege Escalation: When Agents Free Each Other Feedly Summary: Cross-Agent Privilege Escalation: When Agents Free Each Other Here’s a clever new form of AI exploit from Johann Rehberger, who has coined the term Cross-Agent Privilege Escalation to describe an attack where multiple coding agents – GitHub…

  • Embrace The Red: Cross-Agent Privilege Escalation: When Agents Free Each Other

    —

    by

    Kurt Seifried
    in

    Source URL: https://embracethered.com/blog/posts/2025/cross-agent-privilege-escalation-agents-that-free-each-other/ Source: Embrace The Red Title: Cross-Agent Privilege Escalation: When Agents Free Each Other Feedly Summary: During the Month of AI Bugs, I described an emerging vulnerability pattern that shows how commonly agentic systems have a design flaw that allows an agent to overwrite its own configuration and security settings. This allows the…

  • Microsoft Security Blog: Retail at risk: How one alert uncovered a persistent cyberthreat​​

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.microsoft.com/en-us/security/blog/2025/09/24/retail-at-risk-how-one-alert-uncovered-a-persistent-cyberthreat/ Source: Microsoft Security Blog Title: Retail at risk: How one alert uncovered a persistent cyberthreat​​ Feedly Summary: In the latest edition of our Cyberattack Series, we dive into real-world cases targeting retail organizations. With 60% of retail companies reporting operational disruptions from cyberattacks and 43% experiencing breaches in the past year, the stakes…

  • Simon Willison’s Weblog: GPT-5-Codex

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Sep/23/gpt-5-codex/#atom-everything Source: Simon Willison’s Weblog Title: GPT-5-Codex Feedly Summary: GPT-5-Codex OpenAI half-relased this model earlier this month, adding it to their Codex CLI tool but not their API. Today they’ve fixed that – the new model can now be accessed as gpt-5-codex. It’s priced the same as regular GPT-5: $1.25/million input tokens, $10/million…

  • The Register: Nearly half of businesses suffered deepfaked phone calls against staff

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/09/23/gartner_ai_attack/ Source: The Register Title: Nearly half of businesses suffered deepfaked phone calls against staff Feedly Summary: AI attacks on the rise A survey of cybersecurity bosses has shown that 62 percent reported attacks on their staff using AI over the last year, either by the use of prompt injection attacks or faking…