Natural Language Processing news and analysis on Web Pulse: 5440 curated articles tracking the latest Natural Language Processing developments, tools, and research, updated continuously from vetted sources.
An engineer's experiment found that a zero-parameter count table over the current document overtakes a 1.43M-parameter transformer with a fixed 64-token window as documents grow longer. At L=1000 tokens the cache reached…
A developer built the F-072 Semantic Risk Parser, an NLP layer that scans an LLM's unstructured chain-of-thought reasoning for implicit risk markers rather than relying solely on its structured JSON trading decisions. Th…
A developer catalogued a 1,245-object database schema with an LLM, generating natural-language descriptions for each table, and found that retrieval quality dropped sharply rather than improving. The token "contact" went…
Famulor launched a full-duplex AI phone agent that listens while speaking, handling inbound calls, outbound campaigns, and follow-ups across WhatsApp, email, SMS, and a website widget from a single contact record. The ag…
A developer who shipped LectureNotes AI and now builds voice agents argues that long-form lecture transcription and real-time call transcription are fundamentally different problems that fail, are evaluated, and are impr…
Shrijith Venkatramana, an engineer building the AI code review tool LiveReview, traces modern LLM tokenization back to Byte Pair Encoding, a 1994 data-compression algorithm by Philip Gage. The writeup explains how BPE-st…
A developer published a beginner-focused cheat sheet for getting reliable results from Anthropic's Claude AI, built around a five-part prompting formula: Context, Role, Action, Format, and Tone. The guide walks through c…
Search Engine Land published an analysis on April 30, 2026 arguing that backlinks alone are no longer sufficient for SEO authority, as AI-driven search systems increasingly weigh brand mentions, entity data, citations, a…
A paper submitted on 28 Sep 2025 to arXiv's Computer Science > Artificial Intelligence section formalizes the correspondence between fibring of modal logics and fibring of neural networks, a gap the authors say was never…
A developer documented a debugging retrospective on remote chat failover, arguing that reusing a single `status: "streaming"` state for both on-device and remote inference hides origin changes from keyboard and screen-re…
A developer has published a step-by-step recipe for building a Retrieval-Augmented Generation (RAG) legal research assistant that retrieves relevant case law from the CourtListener API, embeds opinions with OpenAI's text…
A developer built Moe, a macOS-native AI assistant that runs in a panel at the notch and can be invoked from any app via a held Option key, a keyboard shortcut, or an on-device "Hey Moe" wake word. The assistant executes…
A developer released aicurt v0.1.1, an open-source Python package that adds retrieval-augmented generation primitives on top of the project's existing PII detection and text sanitization utilities. The update introduces …
Computer science graduate student Ivory Yang at Dartmouth's Guarini School, with collaborators Weicheng Ma and Assistant Professor of Computer Science Soroush Vosoughi, built an AI framework called NüshuRescue that used …
Researchers Ivory Yang, Weicheng Ma, and Soroush Vosoughi presented NüshuRescue, an AI-driven framework for training large language models on endangered languages with minimal data, at COLING 2025 in Abu Dhabi. Using GPT…
Large language models process text as tokens rather than words, and providers charge separately for input and output tokens, usually in price-per-million units, with output tokens almost always costing more per token tha…
OpenAI released the GPT-Live-1 API on September 10, 2026, priced at $0.05 per minute for a full-duplex voice layer that delegates reasoning to developer-chosen backend models. According to Unite.AI, GPT-Live-1 achieves 0…
A Thai AI practitioner's comparative analysis finds that locally trained Thai language models outperform global frontier models on Thai-specific tasks such as document and handwriting recognition, legal citation, Isan di…
A survey of Thai-language AI resources on Hugging Face highlights underused datasets and models, including the OpenThaiGPT evaluation dataset and the WangchanThaiInstruct multi-turn conversation set, alongside SCB 10X's …
Just Tools LTD, developer of the Mac dictation app Clavio, has detailed how it routes dictation by application identity on macOS, using NSWorkspace activation notifications and bundle identifiers to track the live frontm…