source&pool
A daily wire of long-form journalism, video, and discourse — filed, tagged, and laid out flat.
VOL. I·NO. 01
TUESDAY, OCTOBER 6, 2026
Hacker News1942X 主题热门1878CNBC116PANews77Channel News Asia56ChainCatcher51YahooFinance48Coinness42SouthChinaMorningPost35Crypto.news30Verge28aihot279to5Google26TechCrunch21Cointelegraph20IGN19Kotaku19MacRumors199to5Mac18Decrypt17Guardian17CoinDesk16Engadget16Variety16ArsTechnica13FoxBusiness13Gematsu12NBC11Eurogamer10Investor'sBusinessDaily9PushSquare9AndroidAuthority8DW8Gizmodo8Polygon8BitcoinMagazine7Mashable7NintendoLife7TechPowerUp7GSMArena6Motor16NPR6SeekingAlpha6WIRED6AMBCrypto5BBC World5Deadline5DigitalFoundry5GameInformer5XBOXWire5Wccftech5GamesIndustry.biz4Notebookcheck4USAToday4VideoCardz4VideoGamesChronicle4WarhammerCommunity4WindowsCentral4ABC3AlJazeera3bgr3BusinessInsider3CBS3CNET3CNN3DroidLife3Fox3HollywoodReporter3LosAngelesTimes3NintendoEverything3NewYorkPost3Pokemon3SamMobile3Yahoo3TechSpot3Hacker3Register3AndroidPolice2AppleInsider2EIA2Electrek2Euronews2FierceBiotech2Futurism2GAMINGbible2Hackaday2Nature2Phoronix2politico.eu2PureXbox2SeattleTimes2SEC2Space2Autopian2Drive2Tom'sGuide2WhatHi-Fi?2404Media180Level1AboutAmazon1Aftermath1AFTVnews1AlaskaBeacon1AndroidHeadlines1Anthropic1AUTOMATON1AWealthofCommonSense1Barron's1BikeRadar1BleacherReport1BleepingComputer1BlockClubChicago1BuzzFeed1Carscoops1SanDiegoCountyCenter1Draftsim1Endpoints1Federal Reserve1MotleyFool1Fortune1GameFile1GamesBeat1GearPatrol1GeekyGadgets1Hodinkee1How-ToGeek1HuffPost1Independent1InsiderGaming1KOMO1Livingetc1magic.gg1Minecraft1MyNintendo1MyNorthwest1Newsshooter1NoemaMagazine1NYT1CrudeOilPricesToday1PageSix1PCGamesN1PCMag1PCWorld1PetaPixel1PokeBeach1PokémonGOHub1qz1RoadtoVR1RockPaperShotgun1ScreenRant1SearchEngineRoundtable1SlashGear1Slate1statnews1Conversation1MobileReport1TweakTown1WeatherChannel1WindowsLatest195.5WSB1WWD1Yahoo1ZDNET1
  1. 001Hacker NewsOCT · 01English

    Lightweight PDF parser with layout, tables, formulas and bounding boxes

    Papero is a lightweight PDF parser that extracts text, tables, formulas, and layout information without machine learning, running on CPU in browsers, Python, or as an API. It converts PDFs to Markdown, JSON, Word, Excel and other formats while preserving document structure and block positions for use in RAG, search, and LLM applications.

    By Beatrizalmeidaf
  2. 002Hacker NewsOCT · 01English

    Cloudflare AI Search is now generally available

    Cloudflare's AI Search is now generally available, expanding support for multimodal formats including native image embeddings, OCR for PDFs, and larger files up to 10 MiB. The service combines multiple Cloudflare tools into a managed search pipeline and will begin billing on November 1, 2026, while maintaining a free tier.

    By fourfire