source&pool
A daily wire of long-form journalism, video, and discourse — filed, tagged, and laid out flat.
VOL. I·NO. 01
THURSDAY, SEPTEMBER 24, 2026
Hacker News3525X 主题热门3421CNBC61YahooFinance58aihot559to5Mac47MacRumors46Verge39IGN38Kotaku35TechCrunch26AndroidAuthority23Engadget20NintendoLife20Gematsu199to5Google15BusinessInsider15WarhammerCommunity15Eurogamer14Guardian14USAToday14ArsTechnica13Polygon13Wccftech12Fortune11FoxBusiness11PushSquare11Investor'sBusinessDaily10NPR10TechPowerUp10ABC9Gizmodo9NBC9Notebookcheck9SeekingAlpha9CBS8CNN8MotleyFool8GSMArena8NintendoEverything8VideoCardz8VideoGamesChronicle8Yahoo8AppleInsider7CNET7CoinDesk7Fox7PureXbox7BleepingComputer6Mashable6NewYorkPost6Conversation6AlJazeera5bgr5Deadline5PlayStationLifeStyle5TechSpot5Tom'sGuide5WIRED5Aftermath4AndroidPolice4Motor14Nature4XBOXWire4PetaPixel4Pokemon4SamMobile4SouthChinaMorningPost4SlashGear4Variety4WSB-TV4BellofLostSouls3DroidLife3GamesIndustry.biz3Hackaday3HollywoodReporter3HuffPost3InsiderGaming3PokeBeach3RockPaperShotgun3RPGSite3SeattleTimes3SFGATE3UploadVR3WhatHi-Fi?3WindowsCentral3404Media26abcPhiladelphia280Level2ABC7LosAngeles2AndroidCentral2AZFamily2Benzinga2Currently2DCRainmaker2DigitalFoundry2EventHubs2Futurism2GameInformer2HouseDigest2Jalopnik2LosAngelesTimes2Lifehacker2PCMag2qz2Road&Track2SimsCommunity2Slate2TimeExtension2TODAY2TweakTown2YahooFinanceUK224/7WallSt.1BusinessInsiderAfrica1Alternet1AndroidHeadlines1ArizonaSports1BikeRadar1BloodyDisgusting1BostonGlobe1BusinessTimes1Yahoo!FinanceCanada1CalMatters1CarBuzz1cbn1ChromeUnboxed1Chron1ClaimDepot1ColoradoSun1Skin.ClubCommunity1ChristianScienceMonitor1CyberSecurityNews1Cyclingnews1DailyDownforce1DailyKos1DaringFireball1DarkHorizons1Decrypt1Defense1denver71Designboom1DigitalCameraWorld1DirtonDirt1DSOGaming1Electrek1empireonline1GameGPU1erictopol.substack1Fangoria1FOX191franchisetimes1DetroitFreePress1GameRant1GameWorldObserver1GAMINGbible1GamingOnLinux1AAAGasPrices1GearPatrol1GeekWire1GeekyGadgets1Global1GosuGamers1Gothamist1Hackster.io1Hodinkee1HoustonChronicle1Independent1InterestingEngineering1Invezz1MacObserver1Magic:Gathering1MakeUseOf1Mashed1Mercury1MLive1MorningBrew1Motorsport1MP1st1MyNintendo1BloombergLaw1SemiAnalysis1Newsshooter1Newsweek1NintendoWire1nrn1CrudeOilPricesToday1OneMileataTime1OregonPublicBroadcasting1OregonLive1PageSix1PersonaCentral1Phoronix1politico.eu1QuantaMagazine1Realtor1RoadtoVR1RockstarINTEL1Salon1SeattleRed1Semafor1SanFranciscoChronicle1SimpleFlying1GhostHowls1SlippedDisc1SoraNews241SpaceNews1YahooTech1the5krunner1DailyBeast1DailyMeal1Drive1Hacker1Hindu1Intercept1Register1Times1TimesofIndia1TimesUnion1TMZ1TopGear1PCMagUK1VisualCapitalist1Vulture1WCVB1WFMZ1WHYY1WKYT1YGOrganization1YourTango1
  1. 001Hacker NewsSEP · 23English

    Strands Harness

    Anthropic released Strands harness, a general-purpose agent framework available under Apache 2.0 that runs locally or in the cloud. It achieves 28% lower costs than comparable Claude and GPT harnesses while maintaining equal or better accuracy through optimized prompt caching and context management. The framework supports multiple model providers and includes built-in tools for shell, file, and web operations.

    By Arron Bailiss; Albert Zhao; Tim Moreton; Gautam Sirdeshmukh; Murat Kaan Meral; Ariel Nabavian
  2. 002Hacker NewsSEP · 23English

    Unreal Agent An async-first agent harness

    Unreal Labs presents an async-first agent harness library with components for managing LLM agent sessions, tool calls, and asynchronous operations. The system uses event-driven architecture with session-scoped deduplication, append-only persisted history, and composable tool translators that validate and convert model requests into serializable operations.

    By Unreallabsai
  3. 003Hacker NewsSEP · 22English

    Failures shown to be the harness, not the model (blog post)

    A developer tested five coding agents on the same local model (qwen3-coder-next) and frozen test suite, finding that 90% of failures stemmed from harness problems rather than model limitations. The model generated correct code ~97-98% of the time, but agents failed to properly execute, verify, or complete tasks due to tooling issues like hard-coded turn limits and poor stopping conditions.

    By gherlein
  4. 004Hacker NewsSEP · 22English

    RRSI: Regularized Recursive Self-Improvement of Agent Harnesses

    RRSI is a method for automatically improving LLM agent systems by iteratively refining prompts, control flow, and tooling while preventing overfitting through regularization constraints. The approach uses a budget-limited proposer and a critic-pruner selector to favor reusable mechanisms, achieving significant gains on in-distribution and out-of-distribution benchmarks while reducing computational cost.

    By Xia; Peng; Han; Rujun; Wang; Zifeng; Yanfei; Zhang; Yufan; Lee; Yoonho; Huang; Chengsong; CuiZhu; Zhongying; Ming; Yifei; Yao; Huaxiu; Gokturk; Burak; Pfister; Tomas; Chen-Yu
  5. 005Hacker NewsSEP · 18English

    Apprentice: A Slim, Extensible Coding Harness (Written in Common Lisp)

    Apprentice is a highly configurable Common Lisp coding harness for AI agents, built around abstractions for models, tools, anchors, and loops. It supports multiple LLM providers and enables rapid customization through Lisp macros and REPL-driven development.

    By Skarnati
  6. 006Hacker NewsSEP · 17English

    Show HN: Composing domain-specific harness on Python in 10 mins

    Cayu is a Python framework for building domain-specific AI agent harnesses. The article demonstrates assembling a campus dining purchase agent by defining the job, creating an agent identity, building tools that wrap business logic, and providing policies that guide the model's decision-making process.

    By zamir_akimbekov