Experimental News Clipping Site

Tag: long-term memory

  • Embrace The Red: Windsurf: Memory-Persistent Data Exfiltration (SpAIware Exploit)

    —

    by

    Kurt Seifried
    in

    Source URL: https://embracethered.com/blog/posts/2025/windsurf-spaiware-exploit-persistent-prompt-injection/ Source: Embrace The Red Title: Windsurf: Memory-Persistent Data Exfiltration (SpAIware Exploit) Feedly Summary: In this second post about Windsurf Cascade we are exploring the SpAIware attack, which allows memory persistent data exfiltration. SpAIware is an attack we first successfully demonstrated with ChatGPT last year and OpenAI mitigated. While inspecting the system prompt…

  • AWS News Blog: Introducing Amazon Bedrock AgentCore: Securely deploy and operate AI agents at any scale (preview)

    —

    by

    Kurt Seifried
    in

    Source URL: https://aws.amazon.com/blogs/aws/introducing-amazon-bedrock-agentcore-securely-deploy-and-operate-ai-agents-at-any-scale/ Source: AWS News Blog Title: Introducing Amazon Bedrock AgentCore: Securely deploy and operate AI agents at any scale (preview) Feedly Summary: Amazon Bedrock AgentCore enables rapid deployment and scaling of AI agents with enterprise-grade security. It provides memory management, identity controls, and tool integration—streamlining development while working with any open-source framework and…

  • The Cloudflare Blog: Building agents with OpenAI and Cloudflare’s Agents SDK

    —

    by

    Kurt Seifried
    in

    Source URL: https://blog.cloudflare.com/building-agents-with-openai-and-cloudflares-agents-sdk/ Source: The Cloudflare Blog Title: Building agents with OpenAI and Cloudflare’s Agents SDK Feedly Summary: We’re building AI agents where logic and reasoning are handled by OpenAI’s Agents SDK, and execution happens across Cloudflare’s global network via Cloudflare’s Agents SDK. AI Summary and Description: Yes **Summary:** The text provides an in-depth exploration…

  • Hacker News: Some Thoughts on Autoregressive Models

    —

    by

    Kurt Seifried
    in

    Source URL: https://wonderfall.dev/autoregressive/ Source: Hacker News Title: Some Thoughts on Autoregressive Models Feedly Summary: Comments AI Summary and Description: Yes **Summary:** This text offers a comprehensive critique of autoregressive (AR) models, particularly large language models (LLMs), highlighting their strengths and limitations regarding human-like cognition and reasoning. It emphasizes the need for alternative architectures that integrate…

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

    —

    by

    Kurt Seifried
    in

    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…

  • Embrace The Red: Hacking Gemini’s Memory with Prompt Injection and Delayed Tool Invocation

    —

    by

    Kurt Seifried
    in

    Source URL: https://embracethered.com/blog/posts/2025/gemini-memory-persistence-prompt-injection/ Source: Embrace The Red Title: Hacking Gemini’s Memory with Prompt Injection and Delayed Tool Invocation Feedly Summary: Imagine your AI rewriting your personal history… A while ago Google added memories to Gemini. Memories allow Gemini to store user-related data across sessions, storing information in long-term memory. The feature is only available to…

  • Hacker News: HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models

    —

    by

    Kurt Seifried
    in

    Source URL: https://arxiv.org/abs/2405.14831 Source: Hacker News Title: HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models Feedly Summary: Comments AI Summary and Description: Yes Summary: The paper presents HippoRAG, an innovative framework designed to enhance the long-term memory capabilities of Large Language Models (LLMs) by emulating neurobiological processes. This work is particularly relevant for AI…