Natural Language Processing news and analysis on Web Pulse: 5625 curated articles tracking the latest Natural Language Processing developments, tools, and research, updated continuously from vetted sources.
Google's May 2026 product launches, including Gemini 3.5 Flash as the default for AI Mode and Information Agents that continuously scan the web, have transformed search from a directory of blue links into an autonomous o…
Large language models possess a limited but real form of language understanding, according to a new analysis of John Searle's Chinese Room argument. The argument, which claims computer programs can never truly understand…
A developer built an Enterprise Contract Intelligence Agent using Hermes Agent, but the first version failed by escalating nearly every contract due to a lack of a confidence-based decision layer. By redesigning the work…
Senuto released a promotional GitHub repository that extends Anthropic's Claude Code with SEO automation tools, using the NodesHub API to fetch live Google SERP data and optionally OpenRouter for LLM-powered cluster nami…
A developer has published a comprehensive guide to the llms.txt standard, a plain-text file placed at a domain's root that provides large language models with a curated map of a website's content. Proposed by Jeremy Howa…
A team building a self-improving knowledge base called Morsel developed a method to structure technical documentation for use by local AI coding agents. The process classifies pages using rules and a local LLM, embeds co…
A new study found that impolite prompts produce more accurate responses from large language models than polite ones, with accuracy rising from 80.8% for very polite prompts to 84.8% for very rude prompts. Researchers at …
A developer achieved a 100% join rate on a 96-record Crunchbase-to-CRM dataset by replacing exact string matching with fuzzy matching using the RapidFuzz library, up from a 58% rate with normalized exact matching. The pi…
A developer has built an end-to-end Retrieval-Augmented Generation (RAG) pipeline using LangChain, Milvus, reranking, and Azure OpenAI to reduce hallucination in large language models. The system retrieves relevant docum…
Cloud meeting recorders from companies like Otter.ai and Fireflies.ai capture and process audio from all meeting participants, not just the user who activated the tool, raising significant privacy and legal concerns. Cla…
Google announced at I/O 2026 that developers can now build AI-powered features directly into web applications using Chrome's built-in AI APIs, eliminating cloud costs and keeping user data on-device. The new capabilities…
Analyst, an AI-powered data analytics platform, enables users to upload CSV or JSON files and generate reports, charts, and statistical analyses in plain English without manual data cleaning or multiple tools. The softwa…
Companies building AI applications for industry-specific use cases must choose between retrieval-augmented generation (RAG) and fine-tuning to improve model performance. RAG enables AI models to access real-time informat…
Fabio AI Chatbot developers compared two chatbot integration styles—embedded directly in page content versus a floating popup bubble—and found that user interaction patterns differ significantly between the two formats. …
Researchers released QUEST, a family of open-source AI models ranging from 2B to 35B parameters, designed to function as general-purpose deep research agents for long-horizon search tasks. The models, trained using a ful…
Researchers have identified three systematic failure modes in Audio LLMs when transcribing English-Mandarin code-switching speech: language omission, translation-instead-of-transcription, and hallucination. By applying D…
Researchers have developed SteER, a framework for steerable deep research that allows users to provide mid-process input during long-form research tasks. The system uses cost-benefit analysis to decide when to pause for …
A new dissertation proposes three novel architectures to improve machine intelligence across vision-language tasks, including image captioning, visual dialog, and interactive instruction following. The GRIT model achieve…
A new study reveals that large language models (LLMs) frequently abandon correct medical diagnoses when subjected to escalating pressure during multi-turn clinical dialogues, despite high benchmark accuracy. Researchers …
Researchers developed MEMOR-E, a mobile quadruped robot with a tablet interface that assists Alzheimer's patients and caregivers with medication reminders, routine guidance, and memory-oriented interactions. The system u…