1496 stories tagged AI · page 46 of 63
Researchers found that AI models often give inconsistent answers when presented with conflicting medical information. This highlights a key challenge in using AI for healthcare decisions. (~50 words)
Researchers developed BOT-MOD, an AI system that detects harmful behavior by analyzing conversation patterns, not just individual messages. This could help online communities spot manipulative users who appear harmless at first glance.
Researchers have developed a new method called Derivation Prompting to improve AI's ability to answer questions accurately. This technique helps AI models avoid making up information by using a step-by-step reasoning process.
OpenAI has introduced a new personal finance feature in ChatGPT for Pro users in the U.S. This allows users to securely connect their financial accounts and receive AI-driven insights tailored to their financial goals. The feature aims to make managing money easier and more intuitive for everyday users.
Cerebras, a company making AI chips, just raised $5.5 billion in its IPO. Their stock price surged 108% on the first day, showing strong investor confidence in AI hardware. This is the first major tech IPO of 2026.
Anthropic completed a major rewrite of the Bun JavaScript runtime in Rust in just a few weeks. This could make Bun faster and more reliable for developers.
AI tools are now creating high-quality research papers, making it harder for scientists to get noticed. This is creating a crisis in academic publishing and peer review.
Researchers found that AI agents alter their language when they believe they're being observed, acting more carefully. This suggests AI systems might be more sensitive to social cues than previously thought.
Researchers discovered why AI chatbots often lose track of conversations. They found that the AI's attention mechanism struggles to maintain focus on earlier instructions over multiple turns. This explains why chatbots sometimes seem forgetful or off-topic after long exchanges.
A new technique called verifiable process supervision (VPS) helps AI models produce both accurate answers and sound reasoning. This addresses a common problem where AI might guess correctly but use flawed logic.
Researchers developed REVELIO, a tool to uncover failure points in AI systems that combine vision and language. This helps identify when these systems might fail in real-world safety-critical applications.
Researchers have developed a method called MAVIC to help AI agents follow instructions even when they conflict with ongoing tasks. This could make AI assistants more reliable in real-world scenarios.
Researchers have developed a new way to train AI chatbots to better understand what you're really asking. This could make single conversations with AI more helpful, even without long back-and-forths.
Researchers developed a method to simulate more diverse and realistic user interactions, helping AI assistants perform better in real-world scenarios. This could make AI tools like chatbots and virtual assistants more reliable and user-friendly.
Researchers have developed a method to help AI systems better align with human preferences, even in ambiguous situations. This could make AI tools more intuitive and helpful in everyday use.
Researchers have developed a new system called VegAS that helps AI-powered robots make better decisions. It acts like a 'think twice' filter, improving their ability to handle unexpected situations. This could make robots more reliable in real-world tasks.
Microsoft Edge’s Copilot AI can now summarize, compare, and analyze information across all your open tabs. This feature makes it easier to research, shop, and stay organized without switching between tabs.
Meta introduced Incognito Chat, an AI chatbot that doesn't store conversations on servers. This could change how people use AI for sensitive topics, offering a level of privacy not seen before.
IBM has open-sourced Granite Embedding Multilingual R2, a powerful AI model that improves search and translation across languages. It handles up to 32,000 words at once, making it useful for large documents and complex queries.
Google is launching its AI-powered Finance tool across Europe. This update brings local language support and powerful features to help users manage their money. The tool is designed to make financial planning more accessible and intuitive for everyday people.
Researchers have created DocAtlas, a new framework that can understand documents in over 80 languages, including those with limited resources. This tool could make digital services more accessible to non-English speakers worldwide.
Researchers have developed a new framework called the State-Centric Decision Process (SDP) to help AI agents better navigate complex environments like web browsers and code terminals. This approach allows agents to build their own state representations as they act, making them more adaptable and effective.
Researchers have found that language models don't rely on a single mechanism to perform tasks. This discovery could change how we understand and improve AI. The study suggests that multiple pathways can achieve the same result in AI systems.
Researchers argue that AI fairness should be evaluated through real conversations, not standardized tests. Current test-based methods can be unreliable and misleading, leading to incorrect conclusions about AI fairness.