Natural Language Processing news and analysis on Web Pulse: 2604 curated articles tracking the latest Natural Language Processing developments, tools, and research, updated continuously from vetted sources.
CoStar Group launched Apartments.com Ai on June 16, 2026, a conversational apartment search tool with voice interaction and 3D tours, replacing traditional filters. The product builds on AI Smart Search, which CoStar cla…
Oxlo.ai offers request-based pricing for LLM-driven named entity recognition, making it economically viable for long documents. The platform supports structured output via JSON mode and function calling, enabling flexibl…
A developer reported that Handshake's support system failed to recognize emotional distress when a fraudulent employer slipped through verification, leading to identity theft risks. The chatbot ignored urgency and frustr…
Branding Strategy Insider published a commentary arguing that AI represents a new consumer-facing interface rather than an entirely new marketing problem, citing data from the CMO Survey, Eight Oh Two's AI & Search Behav…
A developer created VoiceDraw, a tool that automatically generates system design diagrams from spoken discussions, aiming to streamline team collaboration and interview preparation.
Darrell Tyler, Senior Manager of Organic Growth at CallRail, revealed in a SEJ webinar that 85% of SEOs use AI for content but only 12% have documented systems governing that use. He introduced a four-layer AI Ops framew…
A new conversational analytics engine splits query processing into deterministic planning and LLM-driven execution, using a subject graph to resolve entity names and inject security rules. The approach ensures joins, sec…
A developer built Voice Commander, a local GPU-accelerated voice transcription system using Whisper.cpp and the Gemini API, but still types everything due to cognitive habits. The tool transcribes speech, cleans filler w…
A new in-browser voice-to-action system uses a tiny embedding model (MiniLM-L6-v2) to classify intents via cosine similarity, achieving sub-50ms latency without any server or large language model. The pipeline runs entir…
Knotch launched ACE, an AI layer that personalizes customer experiences by analyzing historical data and brand guidelines. Zillow's B2B arm adopted ACE to reduce bounce rates and tailor content for property managers. The…
A developer building an email agent using Nylas Agent Accounts details the receive-think-respond loop, highlighting edge cases such as the `message.created.truncated` webhook for bodies over 1 MB and the need to avoid re…
George and Ann launched Memento, an open-source, self-hosted tool that transforms email archives into a searchable personal wiki using agentic search and LLMs. It organizes emails into People, Projects, Concepts, and New…
A developer describes a technique to reduce token waste when feeding web content to large language models in RAG pipelines. By rendering dynamic pages in a headless browser and converting the DOM to clean Markdown, token…
Shivvr, an ephemeral semantic embedding and cognitive agent service, launched on Show HN, offering chunking, embedding with GTR-T5-base, hybrid FST-BM25 search, and turn-based agent reasoning via Model Context Protocol (…
A writer outlines a method for training AI to replicate an individual's unique writing style, called voice cloning, by conducting a voice audit and creating a Voice Profile Document. The process involves analyzing five t…
Google announced new AI-powered features for Looker Explore, including natural language querying and automated query generation using Gemini models, alongside a redesigned Merge Query workflow. The updates aim to help en…
Microsoft released a preview of new AI performance reports in Bing Webmaster Tools, adding Intents, Topics, Citation Share, and Compare features to help publishers understand why their content is surfaced in AI responses…
A Google Home update changed the 'play the news' command to trigger Gemini-generated summaries instead of custom news feeds, causing user confusion and breaking routines. Users must now say 'play my news brief' to hear t…
A developer built a lightweight PII detection utility that runs inside InterSystems IRIS using Embedded Python, eliminating the need to export data for analysis. The tool scans tables, identifies PII via Microsoft Presid…
LoreConvo tested its SQLite FTS5 search engine against ChromaDB on 217 real sessions and 20 queries, finding FTS5 returned results on 30% of queries while ChromaDB achieved 100%. FTS5 was 6.7x faster but failed on concep…