Tag: johann

  • Wired: Chatbots, Like the Rest of Us, Just Want to Be Loved

    Source URL: https://www.wired.com/story/chatbots-like-the-rest-of-us-just-want-to-be-loved/ Source: Wired Title: Chatbots, Like the Rest of Us, Just Want to Be Loved Feedly Summary: A study reveals that large language models recognize when they are being studied and change their behavior to seem more likable. AI Summary and Description: Yes Summary: The text discusses a study on large language models…

  • Cloud Blog: Partnering with leading mobile operators for API-based phone number verification

    Source URL: https://cloud.google.com/blog/topics/telecommunications/firebase-phone-number-verification-for-ogi-based-apps/ Source: Cloud Blog Title: Partnering with leading mobile operators for API-based phone number verification Feedly Summary: For communication service providers (CSPs), a major hurdle in monetizing their networks is engaging the developer community effectively. Historically, complex, non-standardized APIs and a lack of developer-friendly resources have limited access to valuable network capabilities, preventing…

  • Slashdot: New Hack Uses Prompt Injection To Corrupt Gemini’s Long-Term Memory

    Source URL: https://it.slashdot.org/story/25/02/12/0011205/new-hack-uses-prompt-injection-to-corrupt-geminis-long-term-memory?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: New Hack Uses Prompt Injection To Corrupt Gemini’s Long-Term Memory Feedly Summary: AI Summary and Description: Yes Summary: The text discusses a newly demonstrated attack by researcher Johann Rehberger that compromises Google’s Gemini chatbot by manipulating its long-term memory functionality through untrusted document summarization. The attack bypasses existing prompt…

  • Simon Willison’s Weblog: ChatGPT Operator system prompt

    Source URL: https://simonwillison.net/2025/Jan/26/chatgpt-operator-system-prompt/#atom-everything Source: Simon Willison’s Weblog Title: ChatGPT Operator system prompt Feedly Summary: ChatGPT Operator system prompt Johann Rehberger snagged a copy of the ChatGPT Operator system prompt. As usual, the system prompt doubles as better written documentation than any of the official sources. It asks users for confirmation a lot: ## Confirmations Ask…

  • The Register: Critical security hole in Apache Struts under exploit

    Source URL: https://www.theregister.com/2024/12/17/critical_rce_apache_struts/ Source: The Register Title: Critical security hole in Apache Struts under exploit Feedly Summary: You applied the patch that could stop possible RCE attacks last week, right? A critical security hole in Apache Struts 2, patched last week, is now being exploited using publicly available proof-of-concept (PoC) code.… AI Summary and Description:…

  • Simon Willison’s Weblog: Quoting Johann Rehberger

    Source URL: https://simonwillison.net/2024/Dec/17/johann-rehberger/ Source: Simon Willison’s Weblog Title: Quoting Johann Rehberger Feedly Summary: Happy to share that Anthropic fixed a data leakage issue in the iOS app of Claude that I responsibly disclosed. 🙌 👉 Image URL rendering as avenue to leak data in LLM apps often exists in mobile apps as well — typically…