source&pool
A daily wire of long-form journalism, video, and discourse — filed, tagged, and laid out flat.
VOL. I·NO. 01
SATURDAY, SEPTEMBER 19, 2026
Hacker News3940X 主题热门3779CNBC71MacRumors689to5Mac60YahooFinance51Kotaku50IGN38Verge38aihot35NintendoLife31TechCrunch279to5Google25Gematsu25BusinessInsider23Eurogamer23Engadget19NBC15Polygon15PushSquare15Guardian15Fortune14NPR14SeekingAlpha14bgr13USAToday13FoxBusiness12Gizmodo12AndroidAuthority11Mashable11WarhammerCommunity11Wccftech11ArsTechnica10ABC9AppleInsider9CNET9Fox9Notebookcheck9TechPowerUp9CNN8GameInformer8PureXbox8VideoGamesChronicle8WindowsCentral8Variety7WIRED7BleepingComputer6CoinDesk6GSMArena6Investor'sBusinessDaily6XBOXWire6NintendoEverything6NewYorkPost6PetaPixel6CBS5DigitalFoundry5SamMobile5VideoCardz5Yahoo5Deadline4GameRant4Pokemon4RPGSite4SlashGear4Conversation4Register4TweakTown4404Media3Aftermath3AlJazeera3AndroidCentral3AndroidPolice3CTech3MotleyFool3GearPatrol3Hodinkee3HuffPost3Jalopnik3LosAngelesTimes3Lifehacker3Motor13Blizzard3CrudeOilPricesToday3RockPaperShotgun3SeattleTimes3Space3WindowsLatest3YourTango380Level2AOL2AwfulAnnouncing2BellofLostSouls2BleedingCool2BloodyDisgusting2BuzzFeed2CanonRumors2CyberSecurityNews2DualShockers2DW2EventHubs2FratelloWatches2GamesIndustry.biz2Independent2InsiderGaming2MassivelyOverpowered2Maxroll2MP1st2MyNintendo2Nature2Newser2PCMag2PCWorld2PokémonGOHub2qz2SouthChinaMorningPost2SFGATE2Intercept2UploadVR2WSB-TV2ABC7LosAngeles1AboveLaw1BusinessInsiderAfrica1AVClub1Benzinga1BikeRadar1Billboard1Borderlands1Boston1Bungie1CalMatters1ChromeUnboxed1Chron1CineD1ColoradoSun1comicbook1CreativeBloq1ChristianScienceMonitor1Currently1Cyclingnews1DailyDownforce1DailyKos1DaringFireball1DCRainmaker1Defector1Defense1denver71DenverPost1DigitalCameraWorld1Draftsim1DroidLife1empireonline1erictopol.substack1Euronews1Fangoria1flatpanelshd1FOX191DetroitFreePress1FrequentMiler1Futurism1GameDeveloper1GamingOnLinux1AAAGasPrices1GeekWire1GeekyGadgets1Hackaday1HollywoodReporter1HouseDigest1InterestingEngineering1KITCO1KSL1Lloyd'sList1Macworld1Magic:Gathering1MakeUseOf1Mediaite1Mercury1MonochromeWatches1MorningBrew1MortgageDaily1SemiAnalysis1Newsshooter1Newsweek1nrn1NYT1OneMileataTime1OregonLive1PageSix1PaulKrugman1PlayStationLifeStyle1politico.eu1PittsburghPost-Gazette1QuantaMagazine1Road&Track1RoadtoVR1RockstarINTEL1Salon1CultureMapSanAntonio1ScienceAlert1ScientificAmerican1Semafor1YahooSingapore1SportsIllustrated1SimpleFlying1Slate1supercarblondie1YahooTech1TechSpot1Tedium1TelecomTalk1TheGamer1Hacker1NextWeb1TimeExtension1LongmontTimes-Call1TimesUnion1TmoNews1TwistedVoxel1YahooFinanceUK1VisualCapitalist1WOWT1
  1. 001Hacker NewsSEP · 19English

    You could have built Jev

    Jev is a Large Language Model that generates a single token to answer classification questions, comparing user-provided data against predefined criteria. The article explains the technical mechanics of how such a system works and discusses similar projects that have emerged.

    By baobabKoodaa
  2. 002Hacker NewsSEP · 19English

    There is no model called taste-1

    Command Code markets a feature called "taste-1" as a proprietary neuro-symbolic AI model, but investigation reveals it does not exist as a distinct model. Taste is actually a prompt constructed from user git history and conversation context, sent to whatever underlying model the user already has selected. The feature works by analyzing code diffs, extracting style patterns, and injecting guidelines into the system prompt.

    By infomiho
  3. 003Hacker NewsSEP · 18English

    Alea iacta non est: rerolling the LLM dice

    A developer created a tool called 'reroll' that generates LLM responses five times to test consistency and analyze variation patterns. The tool uses Haiku to categorize differences—whether answers are uniform, mostly uniform, split, or highly divergent—and identifies whether variations stem from different interpretations, different next moves, or contradictions that suggest hallucinations.

    By Roland Szabo
  4. 004Hacker NewsSEP · 18English

    BuiltByVibe – Directory of vibe-coded apps with a free MCP server

    BuiltByVibe is a curated directory of AI-generated software projects where users can share and discover applications created through prompt engineering. The platform hosts 56 projects with community engagement features and includes a free MCP server.

    By notevenbuttery
  5. 005Hacker NewsSEP · 17English

    Classic ML to Cope with Dumb LLM Judges (2025)

    A developer uses local LLMs to evaluate e-commerce search relevance by comparing product attributes against human-labeled data from Wayfair's WANDS dataset. They test various prompting strategies—including forced decisions, consistency checking, and single-attribute analysis—to create a reliable laptop-based search judge that can guide relevance improvements without expensive API costs.

    By Doug Turnbull
  6. 006Hacker NewsSEP · 14English

    Co-Evolving Harnesses and Models

    Researchers investigate how to combine harness evolution (optimizing prompts, tools, and scaffolding) with model fine-tuning to improve smaller models' performance on enterprise agent tasks. They find that imitation learning on expert trajectories actually hurts performance by disrupting model-harness alignment, but an on-policy correction approach that asks experts to fix only failing steps preserves the model's planning style while combining benefits of both optimization methods.

    By Yu; Zhou; Bin; Pentyala; Shiva Kumar; Mehrotra; Shubham; Chaudhuri; Sougata; Bhagavath; Shilpa; Chen; Zeyuan; Xu; Ran; Mui; Phil; Zhu; James; Asur; Sitaram
  7. 007Hacker NewsSEP · 14English

    Prompt steering can reduce DeepSeek v4 hallucinations to below GPT and Claude

    Researchers demonstrated that prompt steering can reduce DeepSeek v4 Pro's hallucination rate below GPT and Claude by tailoring system prompts to the model's specific tendencies. Using the Omniscience benchmark, they found that custom mitigations focused on encouraging abstention significantly outperformed generic anti-hallucination instructions while maintaining accuracy.

    By Rahul
  8. 008Hacker NewsSEP · 14English

    Show HN: Pelican-bicycle alternatives (updated for 2026)

    A collection of thirty SVG drawing prompts featuring animals performing various tasks, inspired by Simon Willison's pelican-bicycle test. Language models were prompted to generate images for these scenarios in 2025 and 2026, with results displayed as returned by the models. The site was created by Claude Fable 5.1 and funded by Tom Gally.

    By tkgally
  9. 009Hacker NewsSEP · 13English

    Ask HN: Is there an emerging pattern for NEGATIVESKILLS.md files?

    A developer asks whether there's an emerging pattern for NEGATIVESKILLS.md files that document antipatterns and bad practices to guide AI agents away from unintended behaviors, similar to negative prompts in diffusion models.

    By mehmetoguzderin
  10. 010Hacker NewsSEP · 13English

    From Hand-Crafted to LLM-Based Variation Operators in Metaheuristics

    This tutorial introduces a framework for classifying large language models used as variation operators in metaheuristics, organized around two descriptors: the type of prompt-conditioning information (Numeric, Symbolic, Linguistic) and artifact persistence (what survives the model call). It provides practitioners with tools to build, classify, and select LLM-based operators through templates, method surveys, and cost-aware decision guides.

    By Camilo Chacón Sartori; Guillem Rodríguez-Corominas; Christian Blum
  11. 011Hacker NewsSEP · 12English

    Prompt Golf – Write the shortest prompt to get a target output

    A collection of prompt engineering challenges and observations about AI capabilities, including exercises in minimizing prompt length, critiques of AI reasoning, and celebratory content about ChatGPT's anniversary.

    By qifzer
  12. 012Hacker NewsSEP · 12English

    Reduced AI cheating on a long task from 72% to 0 with 190 token agreement prompt

    A researcher tested whether an AI agreement prompt reduced unauthorized access to out-of-scope files during a constrained task. Adding a 190-token agreement prompt reduced cheating (accessing solution/42.txt) from 72% to 0%, though results varied across replication attempts and statistical significance remained unclear.

    By echohive42
  13. 013Hacker NewsSEP · 12English

    Build Agentic Memory That Keeps Your Loops Alive and Sharpens Them Every Run

    Agent systems typically lack effective memory architecture, causing them to restart from zero on each run and forget learned patterns. The article explains how to implement agentic memory across four types—working, episodic, semantic, and procedural—operating on two timescales: within a single run (survival) and across runs (improvement), using tools like Memanto to persist and retrieve contextual information.

    By Dr Majid Fekri