Tag: memory system
-
The Register: MINJA sneak attack poisons AI models for other chatbot users
Source URL: https://www.theregister.com/2025/03/11/minja_attack_poisons_ai_model_memory/ Source: The Register Title: MINJA sneak attack poisons AI models for other chatbot users Feedly Summary: Nothing like an OpenAI-powered agent leaking data or getting confused over what someone else whispered to it AI models with memory aim to enhance user interactions by recalling past engagements. However, this feature opens the door…
-
Hacker News: AgenticMemory: Zettelkasten inspired agentic memory system
Source URL: https://github.com/WujiangXu/AgenticMemory Source: Hacker News Title: AgenticMemory: Zettelkasten inspired agentic memory system Feedly Summary: Comments AI Summary and Description: Yes Summary: The text discusses a novel Agentic Memory system designed specifically for Large Language Model (LLM) agents, enabling dynamic management and organization of memories. This system stands out by offering enhanced capabilities compared to…
-
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…
-
Hacker News: Show HN: Mem0 Browser Extension: Shared Memory Across ChatGPT,Claude,Perplexity
Source URL: https://github.com/mem0ai/mem0-chrome-extension Source: Hacker News Title: Show HN: Mem0 Browser Extension: Shared Memory Across ChatGPT,Claude,Perplexity Feedly Summary: Comments AI Summary and Description: Yes Summary: The Mem0 Chrome Extension enhances interaction with AI assistants by introducing memory capabilities that share context across various platforms, including ChatGPT and Claude. This enables more personalized and efficient conversations,…
-
Hacker News: Show HN: Autotab Instruct – Claude Computer Use with Guardrails for Reliability
Source URL: https://news.ycombinator.com/item?id=42019000 Source: Hacker News Title: Show HN: Autotab Instruct – Claude Computer Use with Guardrails for Reliability Feedly Summary: Comments AI Summary and Description: Yes Summary: The text discusses the development of a desktop application focused on creating reliable AI agents utilizing a computer’s mouse and keyboard. It highlights advancements made with Anthropic’s…