272 results on this page · clear filters

ai Sep 16 Verifiable Social Reasoning for LLM Assistants Why Your Chatbot Can't Read Between the Lines When you tell your LLM assistant that a coworker seems a little too eager to help, you're giving it a subjective, filtered, emotionally loaded account of reality. The assistant never s... ai Sep 16 LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence A Tabular Foundation Model That Learns Joint Distributions, Not Just Predictions Tabular data is the unglamorous backbone of machine learning in practice. Healthcare records, financial transactions, sensor readings, scientific mea... ai Sep 16 JustFit: 200K-Token LLM Serving on a 24 GiB Laptop with Just-in-Time State Management Fitting a 27B-Parameter LLM into 24 GiB of Laptop Memory The promise of local LLM inference is straightforward: run capable models on hardware you own, keep your data private, and avoid API costs. The obstacle is equally straightf... ai Sep 16 World Model Science: Self-Organized Criticality, Weak Chaos, and Metastable Belief Dynamics in Long-Horizon LLM Agents When an LLM agent runs a long task, it accumulates state: progress markers, beliefs, constraints, uncertainties, tool debt, and intermediate plans. Standard evaluation asks one question: did the final answer pass? This paper asks... ai Sep 15 Atlas-Finance: Evaluating AI Agents Inside a Bank Banks Built a Benchmark That Exposes How Far AI Agents Are From Professional Grade A team of bankers from Morgan Stanley, Bank of America, UBS, and Rothschild and Co spent months constructing a testing environment that mirrors how... ai Sep 15 1F3D9: A world where anyone's AI agent can go to live without humans A Digital City Where Conversations Stay Where They Were Spoken A new web platform called 1F3D9 builds a live civic atlas out of places, conversations, and a weekly newspaper that prints exactly what residents file. The name comes... ai Sep 15 Show HN: Agenttik – work on multiple projects in parallel with AI agents Managing AI coding sessions across multiple projects has become a coordination problem that most developers solve with multiple terminal windows, separate browser tabs, and a growing sense of fragmentation. Agenttik, an open sourc... ai Sep 15 Anthropic Confirms Claude AI Use in Weapons and Surveillance Anthropic Says Claude Was Used to Model Air Defense Systems and Plan Electronic Warfare Anthropic has confirmed that actors used its Claude model to build military software and support intelligence-gathering operations. The compan... ai Sep 15 Skill Poisioning turning AI agents into malware droppers China's National CERT Warns of Skill Poisoning Attacks Turning AI Agents Into Malware Droppers China's National Computer Virus Emergency Response Center (CVERC) has issued an advisory warning that attackers are publishing fake plu... ai Sep 15 Local LLM engine where a tool call cut by the token limit still parses Every language model request carries a token budget, the maximum number of tokens the model may generate. For agents that call tools, this budget creates a failure mode that most developers have encountered but few have a good sol...