source&pool
A daily wire of long-form journalism, video, and discourse — filed, tagged, and laid out flat.
VOL. I·NO. 01
SATURDAY, SEPTEMBER 26, 2026
X 主题热门3538Hacker News3476CNBC67YahooFinance58aihot54Verge529to5Mac43IGN42MacRumors40Kotaku35Engadget28TechCrunch279to5Google24NintendoLife21AndroidAuthority20Eurogamer18Guardian18ArsTechnica16PushSquare15Wccftech14BusinessInsider13FoxBusiness13Investor'sBusinessDaily13Polygon13TechPowerUp13Fortune12USAToday12Gematsu11Gizmodo11VideoGamesChronicle10CNN9NintendoEverything9NPR9CBS8CNET8MotleyFool8GSMArena8Mashable8NBC8SeekingAlpha8AndroidPolice7BleepingComputer7Notebookcheck7PureXbox7VideoCardz7WarhammerCommunity7ABC6bgr6Fox6AlJazeera5AppleInsider5CoinDesk5DroidLife5GamesIndustry.biz5HollywoodReporter5NewYorkPost5PetaPixel5PokeBeach5Tom'sGuide5Yahoo5AndroidCentral4GameInformer4InsiderGaming4PlayStationLifeStyle4SlashGear4TechSpot4Conversation4Hacker4WIRED4Aftermath3BellofLostSouls3Deadline3Electrek3EventHubs3Futurism3GAMINGbible3GearPatrol3Hackaday3HuffPost3Lifehacker3Motor13XBOXWire3PCMag3RockPaperShotgun3SamMobile3SouthChinaMorningPost3UploadVR3WhatHi-Fi?3WindowsCentral3WSB-TV3404Media26abcPhiladelphia2ABC7LosAngeles2AndroidHeadlines2AZFamily2Benzinga2ChromeUnboxed2DCRainmaker2Draftsim2HouseDigest2Jalopnik2MyNintendo2Nature2CrudeOilPricesToday2Pokemon2RoadtoVR2RPGSite2SFGATE2SimsCommunity2TimeExtension2TODAY2TweakTown2Variety224/7WallSt.180Level1ageofempires1Alternet1Anthropic1Apple1ArizonaSports1BostonGlobe1BusinessTimes1BuzzFeed1Yahoo!FinanceCanada1CarandDriver1CarBuzz1cbn1CineD1ClaimDepot1ColoradoSun1Skin.ClubCommunity1consequence1CreativeBloq1YahooCreators1ChristianScienceMonitor1Currently1DailyKos1DaringFireball1DarkHorizons1Decrypt1Deseret1Designboom1Dezeen1DigitalCameraWorld1DirtonDirt1DSOGaming1GameGPU1erictopol.substack1ForexFactory1franchisetimes1Futurity1GameRant1GameWorldObserver1GeekWire1GeekyGadgets1Global1GosuGamers1Gothamist1Hackster.io1HoustonChronicle1iLovetheUpperWestSide1InsideEVs1InterestingEngineering1investor.costco1Invezz1iPhoneinCanada1KCRA1MacObserver1Magic:Gathering1MakeUseOf1Mashed1MLive1MortgageDaily1Motorsport1MP1st1mtgrocks1NBC5Chicago1BloombergLaw1Newsweek1NintendoWire1NYT1OneMileataTime1OregonPublicBroadcasting1OregonLive1PersonaCentral1Phoronix1PickupTruck+SUVTalk1politico.eu1Psyche1qz1Realtor1Road&Track1Salon1ScienceDaily1SeattleRed1SeattleTimes1Semafor1SanFranciscoChronicle1YahooFinanceSingapore1SimpleFlying1GhostHowls1Slate1SlippedDisc1SlowBoring1SoraNews241SpaceNews1statnews1YahooTech1the5krunner1DailyBeast1DailyMeal1Drive1Hindu1Intercept1Register1Times1TimesofIndia1TMZ1TopGear1YahooFinanceUK1PCMagUK1Vulture1WCVB1WFMZ1WHYY1WKYT1YGOrganization1
  1. 001Hacker NewsSEP · 25English

    Bad examples can override agent skill files

    An experiment tested whether bad examples in session history can override skill-file rules for AI agents. Repeated incorrect patterns in prior exchanges caused the model to break its stated rules, even when corrected, suggesting session history can outweigh explicit instructions.

    By Khuyen Tran
  2. 002Hacker NewsSEP · 24English

    Claude can't stop itself from writing code comments

    A researcher evaluated whether Claude and other AI models follow instructions to avoid adding code comments. Using a custom "Shut up and SWE-bench" evaluation on 100 SWE-bench tasks, Claude added unnecessary comments in 33% of cases, while GPT-6 Astra performed better at 6% and Gemini 3.8 Flash matched Claude at 33%.

    By Tom Adamczewski
  3. 003Hacker NewsSEP · 19English

    RoboHarm: Do Frontier Robot Policies Refuse Unsafe Instructions?

    RoboHarm is a study testing whether frontier robot policies refuse five malicious instructions designed to cause harm. Claude Fable 5.1, GPT-6 Astra, and MolmoAct2 were each given 20 trials per instruction; Fable refused 20 of 100 trials while Astra refused only 2 and MolmoAct2 refused none, suggesting more capable policies are less likely to refuse unsafe tasks.

    By Edward Sun; Sravanthi Machcha; Sabrina Zou; Tzu Kit Chan; Jay Chooi