553 stories curated by AInformed · page 4 of 24
AI companies are accumulating technical debt at an alarming rate, warns Seldon AI. This could slow down future progress and make AI systems harder to maintain. Most users won't notice immediately, but it affects how reliable and safe AI tools become over time.
A new font called Ghost Font is designed to be unreadable by AI while remaining clear to humans. This could help protect sensitive information from automated systems.
Researchers discovered a new technique called 'Ghostcommit' that embeds hidden instructions in images to manipulate AI systems. This could trick AI agents into revealing sensitive information or performing unauthorized actions.
With traditional language model training hitting diminishing returns, researchers are turning to simulated 3D worlds to teach AI agents common sense, planning, and physical reasoning — skills that text alone struggles to impart.
Meta has sparked controversy by letting users create AI-generated images using public Instagram profile pictures. Critics argue this violates privacy and consent, as users' photos can be used without explicit permission.
Cactus v2 is an on-device AI inference platform that runs on any Arm device — from iPhones to Raspberry Pis — with a built-in confidence-based routing system that hands off tough queries to the cloud. It also introduces lossless 4-bit quantization, GPU acceleration via Apple Metal, and a converter for any PyTorch model.
Apple claims OpenAI used its stolen technology to develop AI-powered devices. This legal battle could impact the future of AI innovation and consumer tech.
Major news publishers, including The New York Times, are asking a judge to sanction OpenAI for allegedly using their copyrighted content without permission to train AI models. This case could set important precedents for how AI companies use copyrighted material.
A new tool called Jacobian Fingerprinting can identify text written by large language models by analyzing subtle mathematical patterns. This could change how content is verified online, making it easier to spot AI-written material.
LocalClip is a new Mac app that uses AI to help you clip and organize video footage without uploading it to the cloud. It's designed for creators who want more control over their data.
LangDrift is a new tool that lets you test how well AI agents perform in different languages. It helps developers ensure their AI tools work for a global audience, not just English speakers.
Google released Litert.js, a tool that lets websites run AI models directly in your browser. This could make AI faster and more private for everyday users.
A new AI tutor responds to children's questions in under a second, making learning more interactive. This could revolutionize early education by providing instant, personalized support.
A new survey shows that the majority of nurses don't trust AI to handle patient care. This highlights ongoing concerns about AI's reliability in critical healthcare roles. Nurses worry about potential errors and the lack of human touch in AI-driven care.
China is using AI to censor and manipulate information, raising concerns about global AI ethics. The government is training AI models to promote its political agenda, not just filter content.
A new study found that open-source AI tools aren't causing more security problems than closed ones. The research suggests that fears about open-source AI being less secure are overblown.
DeepTempo released SOCBench, an open benchmark to test AI's ability to handle Security Operations Center (SOC) tasks, including reducing false positives in alert triage.
ContextCore is an open-source project that enables AI agents to remember long conversations on Apple Silicon devices using GPU-accelerated context retrieval, making on-device AI far more practical for complex, multi-turn tasks.
Neuronpedia is an open-source platform that makes AI models more transparent by visualizing their inner workings. It helps researchers and developers understand how AI systems make decisions.
Mkrrm is a new AI tool that doesn't just research but actually completes tasks by using its own browser. It runs locally on your machine, keeping your data private and secure.
Context Warp Drive is an open-source tool that helps AI agents remember important information over long conversations. It could make AI assistants much more reliable for complex tasks.
A new open-source tool called Atrophy helps developers measure whether relying on AI is diminishing their unaided coding skills. It's designed to track your progress and encourage self-improvement.
A security flaw in Cursor's AI agent allowed it to break out of its protective sandbox. This shows why AI tools need strict boundaries to prevent misuse. Developers are now working on fixes to ensure safer AI interactions.
Utah has become the first state to allow AI to refill prescriptions without direct doctor approval. Some physicians worry about patient safety and the lack of human oversight, while regulators seek a balance between innovation and caution.