Natural Language Processing news and analysis on Web Pulse: 5582 curated articles tracking the latest Natural Language Processing developments, tools, and research, updated continuously from vetted sources.
A developer launched Briefed, a free AI-powered newsletter that personalizes content based on user preferences and refines it through replies. The service generates unique issues for each subscriber and allows one-click …
A developer outlines four technical layers for Generative Engine Optimization (GEO) to get developer sites cited by AI search engines like ChatGPT, Perplexity, Claude, and Google AI Overviews. These include configuring c…
AI-powered mass emails are distorting local politics, particularly around energy and climate issues, by flooding officials with automated messages that appear to be from constituents. This manipulation undermines democra…
AI resume screening systems are disproportionately rejecting newcomer and nonnative-English applicants, with a 2023 Upwardly Global report finding that AI tools misidentified 98% of essays from new English speakers as AI…
Fanfiction communities are launching grassroots efforts to detect AI-generated works, but these detection methods often misclassify human authors and fuel social conflict within fandoms. The movement follows revelations …
A new online test from Lancaster University reveals that people can only identify AI-generated hotel reviews 60% of the time, challenging assumptions about detecting AI writing. The test highlights that common AI 'tells'…
A developer at daïmōnes built an AI that reads Aristotle directly from polytonic Greek manuscripts, arguing that corporate AI tools like ChatGPT produce sanitized summaries that strip away textual complexity and philosop…
Researchers from NUS, Tencent Youtu Lab, and Tsinghua introduced MACT, a multi-agent collaboration framework for visual document understanding that decomposes the task into four specialized agents—planning, execution, ju…
FinMav launched a stock screening tool that lets users search for stocks using plain English queries, translating them into financial filters while showing all parameters applied and flagging potential issues. The AI-pow…
A developer building a coding agent's memory system chose SQLite's FTS5 full-text search over vector search, arguing that for structured, keyword-dense content like stack traces, logs, and error codes, exact-match retrie…
AgentOps Debugger, an agentic application for investigating environmental-compliance history in Peru, revealed six critical bugs only exposed by live model output, not offline tests. The system, designed as offline-first…
OpenAI released three new voice models on May 8, 2026, including GPT-Realtime-2, which brings GPT-5-class reasoning to voice interactions. The model features a 128K context window, reliable tool chaining, parallel tool c…
A developer built an AI-powered photo management app called Swipe Cleaner using SwiftUI and Core ML after struggling with storage issues on their iPhone. The app uses on-device processing with Vision framework for percep…
LectuLibre, an AI-powered book translation platform, built an instant translation help feature that lets readers highlight any phrase and receive a context-aware, human-quality translation within seconds. The feature use…
Papa, an open-source alpha CLI and Python library for Hemingway-style readability linting of Markdown, was released on Show HN. It flags hard sentences, passive voice, adverbs, and complex phrasing, and can run locally o…
A token is a small piece of text that AI models process, not necessarily a whole word. Tokenization splits text into tokens, which are converted into numerical IDs and then into embedding vectors that capture meaning. Un…
A new analysis of retrieval-augmented generation (RAG) systems argues that the optimal retrieval depth k* should be calibrated per pipeline stage and reliability axis, not guessed as a single hyperparameter. The author p…
Researchers found that smaller language models suffer from 'embedding condensation,' where token embeddings collapse into a narrow cone, reducing expressivity. They introduced a dispersion loss to counteract this effect,…
SecondLayer, a Ukrainian legal tech company, proposes training a 860B-parameter Mixture-of-Experts model on a 2 TB corpus of Ukrainian legal data, including 96.2 million court decisions, legislation, and registries. The …
Tripadvisor's AI-generated hotel summaries and chatbot downplay or omit reports of food poisoning, hygiene failures, and sexual harassment, according to consumer group Which? and multiple news outlets. The Riu Palace San…