source&pool
A daily wire of long-form journalism, video, and discourse — filed, tagged, and laid out flat.
VOL. I·NO. 01
FRIDAY, SEPTEMBER 25, 2026
Hacker News3685X 主题热门3630CNBC70YahooFinance62aihot57Verge539to5Mac49IGN47MacRumors41Kotaku37Engadget28TechCrunch279to5Google24AndroidAuthority23NintendoLife21Guardian18ArsTechnica17Eurogamer17BusinessInsider15Investor'sBusinessDaily15Wccftech15USAToday14WarhammerCommunity14FoxBusiness13PushSquare13TechPowerUp13Polygon12Fortune11Gizmodo10Mashable10SeekingAlpha10CBS9CNET9Gematsu9NBC9NintendoEverything9NPR9VideoGamesChronicle9CNN8MotleyFool8GSMArena8Notebookcheck8PureXbox8VideoCardz8ABC7bgr7BleepingComputer7AppleInsider6CoinDesk6Fox6NewYorkPost6WIRED6Yahoo6AlJazeera5AndroidCentral5AndroidPolice5DroidLife5HollywoodReporter5InsiderGaming5PetaPixel5PlayStationLifeStyle5PokeBeach5TechSpot5Tom'sGuide5Aftermath4Deadline4GamesIndustry.biz4SamMobile4SlashGear4Conversation4Hacker4UploadVR4Variety4WindowsCentral4404Media3BellofLostSouls3EventHubs3GameInformer3GearPatrol3Hackaday3HuffPost3Lifehacker3Motor13PCMag3RockPaperShotgun3RPGSite3SouthChinaMorningPost3WhatHi-Fi?3WSB-TV36abcPhiladelphia2ABC7LosAngeles2AndroidHeadlines2AZFamily2Benzinga2ChromeUnboxed2Currently2DaringFireball2DCRainmaker2Futurism2GAMINGbible2HouseDigest2Jalopnik2MyNintendo2Nature2XBOXWire2Pokemon2qz2Road&Track2RoadtoVR2SeattleTimes2SFGATE2SimsCommunity2TimeExtension2TODAY2TweakTown224/7WallSt.180Level1ageofempires1Alternet1Apple1ArizonaSports1BostonGlobe1BusinessTimes1BuzzFeed1Yahoo!FinanceCanada1CalMatters1CarBuzz1cbn1CineD1ClaimDepot1ColoradoSun1Skin.ClubCommunity1consequence1YahooCreators1ChristianScienceMonitor1DailyKos1DarkHorizons1Decrypt1Defense1denver71Designboom1DigitalCameraWorld1DigitalFoundry1DirtonDirt1Draftsim1DSOGaming1Electrek1empireonline1GameGPU1erictopol.substack1Fangoria1ForexFactory1franchisetimes1DetroitFreePress1GameRant1GameWorldObserver1GamingOnLinux1GeekWire1GeekyGadgets1Global1GosuGamers1Gothamist1Hackster.io1Hodinkee1HoustonChronicle1Independent1InsideEVs1InterestingEngineering1investor.costco1Invezz1iPhoneinCanada1LosAngelesTimes1MacObserver1MakeUseOf1Mashed1MLive1MorningBrew1MortgageDaily1Motorsport1MP1st1NBC5Chicago1BloombergLaw1SemiAnalysis1Newsshooter1Newsweek1NintendoWire1nrn1NYT1CrudeOilPricesToday1OneMileataTime1OregonPublicBroadcasting1OregonLive1PersonaCentral1Phoronix1PickupTruck+SUVTalk1politico.eu1QuantaMagazine1Realtor1RockstarINTEL1Salon1SeattleRed1Semafor1SanFranciscoChronicle1YahooFinanceSingapore1SimpleFlying1GhostHowls1Slate1SlippedDisc1SlowBoring1SoraNews241SpaceNews1statnews1the5krunner1DailyBeast1DailyMeal1Drive1Hindu1Intercept1Times1TimesofIndia1TimesUnion1TMZ1TopGear1YahooFinanceUK1PCMagUK1Vulture1WCVB1WFMZ1WHYY1WKYT1YGOrganization1YourTango1
  1. 001Hacker NewsSEP · 25English

    TileRT Takes the Top Spot on AgentX with AMD Instinct MI355X GPUs

    TileRT achieved 469 tokens per second on AMD Instinct MI355X GPUs, topping the InferenceX AgentX leaderboard for inference performance on real-world coding agent workloads. The benchmark measures sustained performance across long-horizon agent tasks with growing context, where TileRT retained approximately two-thirds of its speed even at one-million-token context lengths.

    By pella
  2. 002Hacker NewsSEP · 23English

    MiMo-V3 is getting a new architecture. The core of it, HySparse2, is out today

    MiMo-V3 introduces HySparse2, a new architecture designed for agentic inference that reduces prefill FLOPs by 5× and KV cache size by 4.5× compared to MiMo-V2.6 while improving long-context retrieval. HySparse2 uses two levels of KV sharing—KV Bridging and KV Reuse—along with token-level selection and a unified cache for local and global tokens to optimize the workload of processing short actions followed by long observations.

    By ksec
  3. 003Hacker NewsSEP · 23English

    HySparse2: Hybrid Sparse Attention with Two-Level KV Sharing

    HySparse2 is a hybrid sparse attention architecture designed for long-context language models that improves efficiency through two-level KV sharing between self-decoder and cross-decoder components. It replaces block-level sparsity with token-level sparsity and enables prefill computation to exit early, reducing computational cost and KV-cache storage while maintaining performance on long-context retrieval and multi-turn agent tasks.

    By Wei; Jianyu; Gao; Yizhao; Zhang; Qihao; Shimao; Tang; Zhengju; Cheng; Yu; Zhou; Shengjie; Jiang; Zihan; Song; Yifan; Hailin; Zhao; Liang; Yang; Bo; Wang; Gang; Cao; Shijie; Luo; Fuli