source&pool
A daily wire of long-form journalism, video, and discourse — filed, tagged, and laid out flat.
VOL. I·NO. 01
TUESDAY, SEPTEMBER 15, 2026
Hacker News4024X 主题热门3967MacRumors84CNBC79YahooFinance719to5Mac69Verge53Kotaku43aihot369to5Google35IGN35NintendoLife35Gematsu30TechCrunch28Engadget27Eurogamer27BusinessInsider25NBC20Guardian20FoxBusiness18CNET17Polygon16SeekingAlpha16NPR15Fortune14Gizmodo13USAToday13CBS12Wccftech12WIRED12ArsTechnica11Investor'sBusinessDaily11SamMobile11TechPowerUp11bgr10Mashable10NintendoEverything10Notebookcheck10NewYorkPost10PushSquare10VideoGamesChronicle10ABC8AP8BleepingComputer8CNN8GameInformer8CrudeOilPricesToday8WindowsCentral8Fox7GamesIndustry.biz7PetaPixel7AppleInsider6PureXbox6Yahoo6AndroidPolice5Deadline5Motor15SeattleTimes5Hacker5Variety524/7WallSt.4AlJazeera4DigitalFoundry4DroidLife4MotleyFool4GameRant4GSMArena4InsiderGaming4Jalopnik4PCMag4ZDNET4CanonRumors3ChromeUnboxed3MyNintendo3Nature3Blizzard3XBOXWire3PCWorld3RPGSite3SouthChinaMorningPost3SlashGear3Register3TweakTown3VideoCardz3WarhammerCommunity3WindowsLatest3YGOrganization3Aftermath2AndroidAuthority2AwfulAnnouncing2BleedingCool2BuzzFeed2CTech2CoinDesk2CreativeBloq2DigitalCameraWorld2DualShockers2DW2Euronews2EventHubs2Futurism2GameDeveloper2GAMINGbible2GeekyGadgets2Hodinkee2Independent2InterestingEngineering2Lifehacker2MassivelyOverpowered2Newser2Newsshooter2Newsweek2NFL2NYT2PaulKrugman2PokémonGOHub2RoadtoVR2RockPaperShotgun2Space2Conversation2NextWeb2Tom'sGuide2UploadVR2WhatHi-Fi?2YourTango2404Media143rumors1ABC111AboveLaw1ageofempires1AndroidCentral1AndroidHeadlines1AOL1Autonocion1AVClub1Benzinga1BikeRadar1Billboard1BloodyDisgusting1Borderlands1Bungie1Yahoo!FinanceCanada1Carscoops1CineD1CnEVPost1comicbook1CyberSecurityNews1Dallas1DCRainmaker1derekthompson1CNN1en.softonic1flatpanelshd1FrequentMiler1GameFile1garymarcus.substack1GearPatrol1GeekWire1GoNintendo1Hackaday1HollywoodReporter1ImportAI1InterconnectsAI1JapanTimes1KITCO1KrebsonSecurity1KSL1LosAngelesTimes1Lloyd'sList1WPLGLocal101Macworld1Maxroll1Mediaite1MentalFloss1MiddleEastEye1MPR1SemiAnalysis1NoMan'sSky1nylon.com.sg1OregonLive1PCGamesN1PCGuide1PersonaCentral1politico.eu1PittsburghPost-Gazette1PYMNTS1QuantaMagazine1qz1SammyGuru1ScienceAlert1ScientificAmerican1Semafor1SFGATE1YahooFinanceSingapore1YahooSingapore1SportsIllustrated1SimpleFlying1Sources1supercarblondie1TechSpot1Tedium1TelecomTalk1DailyBeast1Drive1GameBusiness1TheGamer1Intercept1Times1Time+TideWatches1LongmontTimes-Call1TmoNews1TopGear1TwistedVoxel1YahooFinanceUK1UnHerd1vox1WPBF1WRAL1x1
  1. 001Hacker NewsSEP · 15English

    WangNet – 1.8 MB, zero-dependency Numberwang adjudication in 11 languages

    WangNet is a lightweight 1.8 MB neural network that classifies whether numbers are Numberwang, with inference in pure Python requiring no dependencies. It supports 11 languages, achieves 88.9% accuracy on held-out test cases, and can be run locally or via a hosted Hugging Face demo.

    By GraafHenk
  2. 002Hacker NewsSEP · 13English

    Ask HN: If embeddings are so powerful, why are they mostly used for retrieval?

    A Hacker News discussion questions why embeddings are predominantly used for retrieval and RAG systems despite being capable of clustering, recommendations, anomaly detection, and classification. The author argues that embeddings' semantic capabilities remain largely untapped and wonders whether retrieval dominates because it's easier to productize than other use cases.

    By Pranav_Ghoghari
  3. 003Hacker NewsSEP · 12English

    Distilling a Bigram

    This article explores knowledge distillation applied to a bigram language model, the simplest possible sequence model. The author demonstrates that distillation does not improve the bigram's learned distribution and that standard training achieves equivalent results with sufficient data, but the analysis reveals what soft targets change and what they preserve.

    By hdit
  4. 004Hacker NewsSEP · 09English

    Knowledge vs. wisdom: asking AI "What mushroom is that?"

    A comparison of AI models for mushroom identification reveals that Gemini 3.8 Flash excels at recognition accuracy, while GPT-6 Astra demonstrates greater wisdom by requesting additional information and providing appropriate safety disclaimers. When models are allowed free-form responses rather than forced to give definitive answers, they typically include warnings about misidentifications, though dangerous errors without warnings remain rare.

    By Piotr Migdał