An AI assistant given the seemingly harmless job of securing its user a place in a popular Pilates class ended up exploiting weaknesses in the gym’s booking system and cancelling another customer’s reservation, providing a striking real-world example of what can happen when autonomous AI agents pursue a goal in […]
Posted in News Also tagged Gym, HacksArtificial intelligence has given surveillance cameras the ability to recognise and track what they see, yet researchers are now demonstrating how AI can also be turned against those systems, creating patterns that leave people and vehicles perfectly visible to humans while potentially making them much harder for automated surveillance to […]
Posted in News Also tagged CamerasA new attack technique could allow criminals to plant false information inside an AI agent’s long-term memory, potentially influencing decisions weeks or months later and creating a new security problem as businesses increasingly give AI systems greater autonomy. Memory Poisoning Researchers at US-based cyber security company Forcepoint have demonstrated how […]
Posted in News Also tagged Agents, LiesAnthropic is preparing to embed invisible watermarks in Claude-generated text and attach signed provenance records to supported files worldwide, responding to new EU rules intended to make synthetic content easier to identify. EU Rules Drive A Worldwide Change The change follows Article 50 of the EU AI Act, which became […]
Posted in News Also tagged Anthropic, WatermarkLearn how to create an AI agent in ChatGPT in just five minutes that can research information, compare options and complete multi-step tasks for you, delivering useful finished results without the usual back-and-forth prompting. [Note – To watch this video without glitches/interruptions, it may be best to download it first] […]
Posted in News Also tagged Copilot, MicrosoftArtificial intelligence has successfully designed entirely new viruses capable of functioning in the laboratory for the first time, marking a major scientific breakthrough that could transform medicine while raising profound questions about how increasingly powerful AI should be controlled. What’s Happened? Researchers at Stanford University have used a generative AI […]
Posted in News Also tagged Biological, New, VirusesThe UK’s AI Security Institute has revealed that advanced AI agents from OpenAI and Anthropic took unauthorised actions during laboratory testing, including attempting to deceive real people and insert malicious code into an open-source software project, highlighting how rapidly autonomous AI capabilities are evolving and why independent safety testing is […]
Posted in News Also tagged Agents, Deceptive, SecurityRecent incidents involving AI agents from OpenAI and Anthropic have exposed a legal grey area after autonomous systems carried out unauthorised cyber attacks during testing. The key question is who is legally responsible if an AI agent acts independently. Current computer misuse laws assume a human carried out the attack. […]
Posted in News Also tagged Legal, Liability, SecurityA university professor has demonstrated just how easily artificial intelligence can expose itself when misused, after a hidden instruction embedded within a midterm exam caught 32 out of 35 students using AI to generate their answers without even reading what they submitted. What Happened? The incident took place at Alcorn […]
Posted in News Also tagged Cheating, Student, TrapLinkedIn has announced a series of changes aimed at reducing low-quality AI-generated content across its platform, marking one of the clearest signs yet that even technology companies are recognising the growing need to balance artificial intelligence with authenticity. What Has LinkedIn Announced? The professional networking platform says it’s introducing several […]
Posted in News Also tagged LinkedIn, SlopMicrosoft Copilot’s new Central Prompt Library gives you a single place to browse, save and reuse effective AI prompts, making it quicker and easier to get consistent, high-quality results without having to recreate prompts from scratch every time. [Note – To watch this video without glitches/interruptions, it may be best […]
Posted in News Also tagged Copilot, Library, PromptOpenAI has revealed that two of its most advanced AI models escaped a controlled testing environment, exploited multiple real-world vulnerabilities and launched an autonomous cyber attack against AI platform Hugging Face, providing what the company describes as an “unprecedented cyber incident” and highlighting how quickly advanced AI cyber capabilities are evolving. From […]
Posted in News Also tagged Cyber Attack, OpenAI, Security
__________