source&pool
A daily wire of long-form journalism, video, and discourse — filed, tagged, and laid out flat.
VOL. I·NO. 01
TUESDAY, SEPTEMBER 22, 2026
Hacker News3778X 主题热门3660CNBC779to5Mac57MacRumors57YahooFinance52Kotaku38IGN35Verge35aihot27TechCrunch259to5Google24Gematsu24NintendoLife23BusinessInsider19Eurogamer17Polygon15PushSquare15Engadget14NPR14Guardian14WarhammerCommunity14NBC13AndroidAuthority12Fortune12Notebookcheck12USAToday12Wccftech12FoxBusiness11AppleInsider10ArsTechnica10CoinDesk10TechPowerUp10ABC9Mashable9SeekingAlpha9bgr8CBS8CNN8Gizmodo8PureXbox8Yahoo8MotleyFool7Investor'sBusinessDaily7NintendoEverything7PetaPixel7Conversation7VideoCardz7GSMArena6SamMobile6VideoGamesChronicle6WIRED6BleepingComputer5CNET5Fox5GameInformer5Pokemon5RockPaperShotgun5AndroidCentral4AndroidPolice4DigitalFoundry4Motor14XBOXWire4NewYorkPost4RPGSite4SlashGear4TechSpot4Variety4WindowsCentral4WSB-TV4Aftermath3AlJazeera3BellofLostSouls3Deadline3Hodinkee3HuffPost3MP1st3PlayStationLifeStyle3SouthChinaMorningPost3SeattleTimes3Register3Tom'sGuide3TweakTown3404Media26abcPhiladelphia280Level2ABC7LosAngeles2BleedingCool2CTech2CanonRumors2DCRainmaker2DigitalCameraWorld2DW2EventHubs2FratelloWatches2Futurism2GameRant2GamesIndustry.biz2GearPatrol2HouseDigest2InsiderGaming2LosAngelesTimes2Lifehacker2Nature2PCMag2PokeBeach2qz2Intercept2TimeExtension224/7WallSt.1BusinessInsiderAfrica1Alternet1AndroidHeadlines1AOL1ArizonaSports1Benzinga1BikeRadar1Billboard1BloodyDisgusting1Boston1Bungie1BusinessTimes1BuzzFeed1CalMatters1CarBuzz1cbn1ChromeUnboxed1Chron1ClaimDepot1ColoradoSun1ChristianScienceMonitor1Currently1CyberSecurityNews1Cyclingnews1DailyDownforce1DailyKos1DaringFireball1DarkHorizons1Decrypt1Defector1Defense1denver71DenverPost1DirtonDirt1Draftsim1DroidLife1DSOGaming1DualShockers1empireonline1erictopol.substack1Euronews1Fangoria1FOX191DetroitFreePress1GameDeveloper1GamingOnLinux1AAAGasPrices1GeekWire1GeekyGadgets1Global1Hackaday1HollywoodReporter1HoustonChronicle1Independent1Invezz1Jalopnik1KITCO1Magic:Gathering1MakeUseOf1Mashed1Maxroll1Mercury1MLive1MonochromeWatches1MorningBrew1MortgageDaily1Motorsport1MyNintendo1Newser1SemiAnalysis1Newsshooter1Newsweek1nrn1CrudeOilPricesToday1OneMileataTime1OregonPublicBroadcasting1OregonLive1PageSix1politico.eu1QuantaMagazine1Road&Track1RoadtoVR1RockstarINTEL1Salon1CultureMapSanAntonio1ScienceAlert1Semafor1SFGATE1YahooSingapore1Slate1SlippedDisc1Space1SpaceNews1YahooTech1the5krunner1DailyBeast1DailyMeal1Drive1Hacker1Hindu1NextWeb1Times1TimesofIndia1TimesUnion1TMZ1YahooFinanceUK1UploadVR1VisualCapitalist1WindowsLatest1WKYT1WOWT1YourTango1
  1. 001Hacker NewsSEP · 22English

    Can gzip be a language model?

    A researcher explores whether gzip, a standard compression utility, can perform language modeling by leveraging the mathematical equivalence between compression and prediction. Using beam search over byte sequences scored by gzip's compression length, they demonstrate that gzip can generate text continuations that show understanding of source material, despite producing imperfect output.

    By Nathan Barry June
  2. 002Hacker NewsSEP · 22English

    You're predictable. That's a good thing: Can personal LLMs learn your judgment?

    A new approach uses personal computer use data to train local LLMs that predict user judgment and writing patterns, reducing the effort required to prompt AI agents. In a two-week study, a specialized model achieved 17.1% semantic accuracy on next-write predictions at $0.3 per call, with a continually trained version reaching 3.0% accuracy at $0.01 per call, suggesting potential for scaling.

    By Hands; Precursor Labs
  3. 003Hacker NewsSEP · 21English

    Models Watching Models

    Jev is a machine learning tool-call classifier that monitors agentic AI executions. While useful for measuring progress and reducing time/spend prediction errors by ~18-19%, it struggles with security (easily bypassed) and detecting lazy agents, making it best suited for observability rather than threat detection.

    By Southbridge AI; Hrishi Olickel
  4. 004Hacker NewsSEP · 20English

    A Model for Winning Survivor

    An article describes building a machine learning model to predict Survivor winners and eliminations. The model uses logistic regression trained on historical data from 50 seasons, analyzing features like confessional time, votes received, advantages, and age to forecast each player's probability of winning or being voted out next.

    By evakhoury
  5. 005Hacker NewsSEP · 19English

    Analyze trends, Measure sentiment, Predict what comes next

    HeronLoom is a tool that transforms social media posts and documents into a 3D graph for analyzing trends, sentiment, and predictions using iterative clustering and LLM-based analysis. It tracks how topics and narratives evolve over time while preserving conflicting interpretations and maintaining evidence-based confidence scores with citations to source material.

    By Korries
  6. 006Hacker NewsSEP · 17English

    What happens when you send a message to an LLM (the API call explained)

    Large Language Models are stateless prediction machines that lack memory between API calls. To create the illusion of conversation, the entire message history is sent with each API request in a messages array, where each message is labeled with a role (user, assistant, or system) to provide context the model cannot infer on its own.

    By Meraki