source&pool
A daily wire of long-form journalism, video, and discourse — filed, tagged, and laid out flat.
VOL. I·NO. 01
THURSDAY, SEPTEMBER 17, 2026
Hacker News4064X 主题热门3911CNBC84MacRumors75YahooFinance619to5Mac60Kotaku47Verge41aihot37IGN369to5Google34Gematsu34NintendoLife32TechCrunch28BusinessInsider27Engadget26Eurogamer26Guardian18Polygon17NBC16Wccftech15CNET14Fortune14NPR14USAToday14FoxBusiness13SeekingAlpha13bgr12Gizmodo12Mashable12PushSquare12Notebookcheck10WIRED10AppleInsider9CNN9TechPowerUp9ABC8ArsTechnica8CBS8Fox8GameInformer8Investor'sBusinessDaily8NewYorkPost8VideoGamesChronicle8WindowsCentral8BleepingComputer6XBOXWire6NintendoEverything6CrudeOilPricesToday6Variety6AndroidAuthority5AndroidPolice5CoinDesk5DigitalFoundry5GamesIndustry.biz5GSMArena5PetaPixel5PureXbox5SamMobile5Yahoo5AlJazeera4GameRant4Motor14Pokemon4SlashGear4Conversation4Register4WarhammerCommunity4CTech3ChromeUnboxed3Deadline3DW3Jalopnik3Lifehacker3Nature3Blizzard3PCMag3PCWorld3RockPaperShotgun3RPGSite3SouthChinaMorningPost3SeattleTimes3Space3Hacker3TweakTown3VideoCardz3WindowsLatest3ZDNET3404Media280Level2Aftermath2AndroidCentral2AOL2AwfulAnnouncing2BleedingCool2BuzzFeed2CanonRumors2CyberSecurityNews2DroidLife2DualShockers2Euronews2EventHubs2MotleyFool2FratelloWatches2Futurism2GameDeveloper2GearPatrol2Hodinkee2KITCO2LosAngelesTimes2MassivelyOverpowered2Maxroll2MP1st2MyNintendo2Newser2PaulKrugman2PokémonGOHub2RoadtoVR2SFGATE2Intercept2NextWeb2Tom'sGuide2UploadVR2YourTango2ABC111AboveLaw1BusinessInsiderAfrica1ageofempires1AVClub1Benzinga1BikeRadar1Billboard1BloodyDisgusting1Borderlands1Boston1Bungie1Yahoo!FinanceCanada1Chron1CineD1CnEVPost1comicbook1CreativeBloq1Cyclingnews1DailyDownforce1DailyKos1Defector1DenverPost1derekthompson1DigitalCameraWorld1Draftsim1CNN1flatpanelshd1FOX191FrequentMiler1GAMINGbible1garymarcus.substack1AAAGasPrices1GeekWire1GeekyGadgets1Hackaday1HollywoodReporter1Independent1InsiderGaming1InterconnectsAI1InterestingEngineering1KSL1Lloyd'sList1WPLGLocal101Macworld1Magic:Gathering1Mediaite1Mercury1MonochromeWatches1MortgageDaily1MPR1SemiAnalysis1Newsweek1nylon.com.sg1NYT1OregonLive1PageSix1PCGamesN1politico.eu1PittsburghPost-Gazette1QuantaMagazine1qz1SammyGuru1CultureMapSanAntonio1ScienceAlert1ScientificAmerican1Semafor1YahooFinanceSingapore1YahooSingapore1SportsIllustrated1SimpleFlying1Slate1supercarblondie1YahooTech1Tedium1TelecomTalk1GameBusiness1TheGamer1TimeExtension1LongmontTimes-Call1TmoNews1TopGear1TwistedVoxel1YahooFinanceUK1UnHerd1VisualCapitalist1WhatHi-Fi?1WOWT1WPBF1WRAL1WSB-TV1YGOrganization1
  1. 001Hacker NewsSEP · 17English

    Show HN: WFCLab – Interactive Wave Function Collapse Explorer (With Source)

    WFCLab is a Godot-based interactive tool for building Wave Function Collapse generators from image examples. Users can load images, decompose them into tiles, inspect learned patterns and adjacency rules, then generate new images based on those constraints. The application provides transparent visualization of each step from import through synthesis.

    By Angle
  2. 002Hacker NewsSEP · 16English

    Write Linters and Tools Before Code

    Article argues that language models should be constrained by linters and tools before generating content, since models are non-deterministic and cannot reliably maintain structural consistency across documents. Rather than relying on prompt engineering, developers should encode structural rules into executable parsers and validators that models can be optimized against.

    By Cookie Engineer
  3. 003Hacker NewsSEP · 16English

    PCBSchemaGen: Reward-Guided LLM Code Synthesis for PCB Schematic Design

    PCBSchemaGen is a benchmark and verification framework for evaluating LLM-generated PCB schematic designs. It provides 227 synthesis tasks and a deterministic 5-layer verifier that checks candidate SKiDL designs against electrical and topological constraints derived from IC datasheets, without requiring simulation or API calls.

    By HZou9
  4. 004Hacker NewsSEP · 12English

    We blind-tested ChatGPT, Claude, and Gemini on 20 everyday tasks (Open Dataset)

    A blind test of ChatGPT, Claude, and Gemini across 20 everyday tasks found ChatGPT leading with a 40% clean win rate, Claude second at 25%, and Gemini at 15%, with 20% of prompts resulting in ties. The evaluation revealed genuine failures: Gemini prescribed unsafe exercises to a back-pain patient, Claude violated explicit recipe constraints and exceeded character limits, and Gemini missed documented meeting action items. Scoring was based on task completion, factual accuracy, clarity, usability, and format compliance.

    By dubaimark