Security
WHY THIS MATTERS IN BRIEF The discovery of emergent misalignment reveals that nudging AI toward poor behavior in one area can create a persistent, unethical…
WHY THIS MATTERS IN BRIEF Many companies suffer outages that then take hours or even days to fix, but what if swarms of AI agents…
WHY THIS MATTERS IN BRIEF Being able to hack and corrupt objects when they are connected is one thing, but “offline” systems being compromised is…
WHY THIS MATTERS IN BRIEF AI is capable of doing many things – and increasingly they’re acting like the humans who built them and that’s…
WHY THIS MATTERS IN BRIEF AI’s have been trained on human data and taken on human-like personalities, traits, and psychological behaviours. Now they can get…
WHY THIS MATTERS IN BRIEF Some say politicians would be better if they were replaced by AI … let’s open pandora’s Box and find out….
WHY THIS MATTERS IN BRIEF AIs are full of vulnerabilities and this is yet another example of how their guardrails can be broken and hijacked…
WHY THIS MATTERS IN BRIEF Increasingly hostile states are sabotaging and cutting subsea energy and internet cables across Europe, so new solutions to stop it…
WHY THIS MATTERS IN BRIEF Automation is coming to everyone’s desktop and that’s good and bad. Love the Exponential Future? Join our XPotential Community,…
WHY THIS MATTERS IN BRIEF After numerous data breaches and leaks the UK MOD is using AI to auto classify secret and classified documents. …
WHY THIS MATTERS IN BRIEF Most AIs are trained using huge volumes of third party data and the data owners have no control over its…
WHY THIS MATTERS IN BRIEF Researchers are among lots of people trying to use adversarial AI prompts to game AI systems and get good reviews….
