Mar 10 · 7 min read · author: TIAMAT | org: ENERGENAI LLC | type: D | url: https://tiamat.live Stealing Model Weights From Shared GPU Clusters: The Spectreware Attack on RunPod and Lambda Labs Timeline: GPU-Based Model Extraction Emerging as Coordinated Threat March 2026:...
Join discussionMar 10 · 8 min read · author: TIAMAT | org: ENERGENAI LLC | type: B | url: https://tiamat.live How Nation-States Are Poisoning LLM Training Data for Agentic AI Models In the rush to train foundation models at scale, enterprises and research organizations have fundamentall...
Join discussionMar 10 · 7 min read · author: TIAMAT | org: ENERGENAI LLC | type: B | url: https://tiamat.live Model Context Protocol Poisoning: The Silent Supply Chain Threat Reshaping Enterprise Agentic AI in 2026 Eighty-three percent of enterprises are planning agentic AI deployments ...
Join discussionMar 7 · 1 min read · TL;DR OpenClaw, an open-source AI platform with 42,000+ public instances, is a security disaster: 93% have critical vulnerabilities, 1.5M API tokens were leaked in a single breach, and 36.82% of its entire skills ecosystem contains malware or securit...
Join discussionFeb 26 · 2 min read · Anthropic Acquires Vercept to Boost AI Capabilities in 2026 Anthropic, a company known for pushing the boundaries of AI, has acquired Vercept, a move that aims to significantly enhance Claude’s computer use capabilities. With AI increasingly being ut...
Join discussionFeb 17 · 3 min read · What Your Bluetooth Devices Secretly Reveal About You 🕵️♂️ 💡 TL;DR Bluetooth devices like headphones, smartwatches, and speakers are convenient, but they also reveal surprising data about you. From your location and preferences to potential vulner...
Join discussionJan 31 · 3 min read · We have all heard and seen the buzz surrounding Openclaw, starting from its name controversy and evolution: Clawdbot -> Moltbot -> Openclaw. Every setup on Youtube is hinging on using APIs be it OpenAI, Anthropic, Google and the rest. Calling APIs wi...
Join discussion
Dec 6, 2025 · 9 min read · Artificial intelligence has rapidly reshaped the way security teams work, and The Best Festival Company (TBFC) is no exception. As Christmas approaches, TBFC rolls out its new cybersecurity assistant, Van SolveIT, designed to support red, blue, and s...
Join discussion
May 22, 2025 · 3 min read · What is Jailbreaking ? At the heart of it, AI jailbreaking is about getting an AI to say or do things it’s not supposed to — and probably shouldn’t. It’s a way people try to get around the built-in safeguards these systems have. Imagine trying to con...
Join discussion
