Natural Language Processing news and analysis on Web Pulse: 3922 curated articles tracking the latest Natural Language Processing developments, tools, and research, updated continuously from vetted sources.
ImageSage, a private, local AI photo gallery app for Windows 11, is now available free from the Microsoft Store. The app uses on-device AI to let users search photos by visual content, text within images via OCR, or file…
A developer created a system prompt designed to stop AI models from writing social media posts with the generic, polished style typical of LinkedIn and X thought leaders. The prompt enforces rules such as banning fake co…
A developer is building MyMangaList, a manga discovery and reading project, and exploring the technical challenges of AI-assisted manga translation. The project aims to make it easier for readers to explore different man…
Divyakush Punjabi, a full-stack and AI systems engineer, built the GovernAI Research Atlas, a semantic discovery platform that unifies research across papers, repositories, and policy. The platform uses ChromaDB vector s…
Hugging Face tests on 11 open-source automatic speech recognition models found several reproduced benchmark transcripts verbatim even when the audio contradicted them, exposing a 10–20% overstatement of real-world accura…
A developer built sentencify, a lightweight JavaScript library that adds punctuation to speech-to-text and LLM output without calling a model. The library uses ordered regular expressions to classify sentences as interro…
A new study finds that lexical BM25 retrieval outperforms sophisticated agentic search methods on large corpora, achieving 50.5 accuracy versus 30.7 for File-System Agent at the largest scale. The gap widens with corpus …
Table Canon, an open-source tool by developer Josh, aims to solve tabletop RPG session memory by using an AI pipeline that emits atomic state deltas from each session to keep context bounded, but the author notes the rep…
A developer building a local-first phone assistant for their solo consulting practice is tackling the problem of missed calls and fragmented client communication. The system uses locally running AI models—Whisper for tra…
A developer has published a guide for building an AI automation agency that offers voice AI agents to local businesses. The service uses n8n, Anthropic's Claude, ElevenLabs, and Twilio to create a hands-free phone front …
A post-mortem by the operator of a 50,000-account paranormal record site found that its two-stage classifier accepted 11 of 14 denial sentences as evidence, including scoring "I have never seen a shadow figure in my bedr…
Krasyn ran its Note Check tool against Omi Health's public scribe benchmark, testing 36 transcript-note pairs from six frontier models. The tool agreed with the benchmark's clean notes but disagreed on nearly every note …
X launched its Managed Campaign Protocol (MCP) on August 21, enabling AI agents like Grok and Anthropic's Claude to create, manage, and optimize ad campaigns through natural language, with all new campaign elements start…
Google announced on Friday that its Google app will soon let users customize their Discovery feed using natural language prompts, powered by Gemini, such as "show me kitchen renovation tips and ideas," with the feature r…
Airtxt, a new dictation app priced at $9, claims to undercut Wispr Flow's $15 subscription while offering on-device or cloud processing, meeting transcription, and keyboard integration across all apps. The app's website,…
Towards Data Science reports that row-level chunks, where each body row of a table is paired with its column headers, can serve as the unit of retrieval in retrieval-augmented generation (RAG) systems, often returning th…
Pythonaibrain-NLP 0.2.0, a structured NLU/NLG framework for Python, is now available on PyPI and GitHub. The framework separates understanding, dialogue state, retrieval, and generation into explicit components, using a …
VLM Run, founded by CEO Sudeep Pillai, launched an OpenAI-compatible gateway on August 19 that routes document-processing work across six open OCR and vision-language models, including GLM-OCR, DeepSeek-OCR-2, dots.mocr,…
Video to Prompt, a free AI tool, generates editable English prompts from short videos or YouTube Shorts links, extracting visual style, subject, action, lighting, camera movement, and audio cues. The free tier allows 1 a…
A new arXiv preprint (2608.19299v1) reports that large language models can generate operationally realistic air traffic control transmissions, but only with lightly constrained prompts and in-context examples. In experim…