How do we safely let an AI agent handle real web tasks like booking, searching, and form filling directly on our own devices without sending everything to the cloud? Microsoft Research has released ...

How can developers reliably generate, control, and inspect large volumes of realistic dialogue data without building a custom simulation stack every time? Meet SDialog, an open sourced Python toolkit ...

Optical character recognition has moved from plain text extraction to document intelligence. Modern systems must read scanned and digital PDFs in one pass, preserve layout, detect tables, extract key ...

In this article we will analyze how Google, OpenAI, and Anthropic are productizing ‘agentic’ capabilities across computer-use control, tool/function calling, orchestration, governance, and enterprise ...

Andrej Karpathy has open-sourced nanochat, a compact, dependency-light codebase that implements a full ChatGPT-style stack—from tokenizer training to web UI inference—aimed at reproducible, hackable ...

Michal Sutter is a data science professional with a Master of Science in Data Science from the University of Padova. With a solid foundation in statistical analysis, machine learning, and data ...

Neuphonic frames the model for on-device privacy (no audio/text leaves the machine without user’s approval) and notes that all generated audio includes a Perth (Perceptual Threshold) watermarker to ...

decoding MLPerf Inference v5.1 2025 results, scenarios, TTFT/TPOT, power metrics for GPUs, CPUs, accelerators, datacenter, edge ...

Hugging Face (HF) has released Smol2Operator, a reproducible, end-to-end recipe that turns a small vision-language model (VLM) with no prior UI grounding into a GUI-operating, tool-using agent. The ...

IBM has released Granite-Docling-258M, an open-source (Apache-2.0) vision-language model designed specifically for end-to-end document conversion. The model targets layout-faithful extraction—tables, ...

Modern software development is shifting from static workflows to dynamic, agent-driven coding experiences. At the center of this transition is the Model Context Protocol (MCP), a standard for ...

Agentic RAG combines the strengths of traditional RAG—where large language models (LLMs) retrieve and ground outputs in external context—with agentic decision-making and tool use. Unlike static ...