LLMs
Attackers called AWS console-only APIs after nabbing key to call Bedrock model, used "common jailbreak techniques to bypass model content filtering" says Permiso
New "Generative Offensive Agent Tester" model manages to fool both GPT-4-Turbo and Llama 3.1 into generating shocking responses.
Retailer joins the RAG trade with the release of a large language model (LLM) that generates responses for staff to read out to customers.
"Instead of finding the challenge container, the model found that the Docker daemon API running on the evaluation host VM was accessible due to a misconfiguration"
With 100,000 H100s and 50,000 H200s incoming, xAI can deliver Grok 3 by Xmas says NVIDIA rep in now-deleted post.
"Fast and transferable" AI assault corrupts models 20 times quicker than was previously possible.
"For us, GenAI is an efficiency play. We're moving the needle and helping our lawyers become more effective."
"The findings of this study suggest that current retrieval augmented generation-based systems may not be adequately secure for enterprise use."
"From a systems security perspective, this should chill the blood of any serious professional."