source&pool
A daily wire of long-form journalism, video, and discourse — filed, tagged, and laid out flat.
VOL. I·NO. 01
WEDNESDAY, SEPTEMBER 16, 2026
Hacker News3861X 主题热门3739CNBC82MacRumors79YahooFinance679to5Mac62Verge45Kotaku44IGN35NintendoLife349to5Google33aihot32Gematsu32Eurogamer27Engadget26TechCrunch26BusinessInsider25Guardian20NBC16NPR16CNET15FoxBusiness14Polygon14Fortune13SeekingAlpha13bgr12Gizmodo12CBS11Mashable11PushSquare11USAToday11Wccftech11WIRED11Investor'sBusinessDaily10TechPowerUp10GameInformer9NintendoEverything9ABC8CNN8Notebookcheck8NewYorkPost8CrudeOilPricesToday8VideoGamesChronicle8ArsTechnica7Fox7WindowsCentral7BleepingComputer6PetaPixel6AppleInsider5Deadline5DigitalFoundry5GamesIndustry.biz5SamMobile5Variety5Yahoo5AlJazeera4AndroidPolice4CoinDesk4DroidLife4MotleyFool4GameRant4GSMArena4Jalopnik4PureXbox4SlashGear4Hacker4AP3BuzzFeed3CTech3CanonRumors3ChromeUnboxed3DW3GameDeveloper3Lifehacker3Motor13Blizzard3XBOXWire3PCMag3PCWorld3SeattleTimes3Space3Register3TweakTown3YGOrganization3ZDNET324/7WallSt.2Aftermath2AndroidCentral2AOL2AwfulAnnouncing2BleedingCool2DigitalCameraWorld2DualShockers2Euronews2EventHubs2Futurism2GearPatrol2Hodinkee2Independent2KITCO2MassivelyOverpowered2MyNintendo2Nature2Newser2Newsweek2PaulKrugman2PokémonGOHub2RoadtoVR2RockPaperShotgun2RPGSite2Conversation2Intercept2NextWeb2Tom'sGuide2UploadVR2VideoCardz2WarhammerCommunity2WindowsLatest2YourTango2404Media143rumors1ABC111AboveLaw1ageofempires1AndroidHeadlines1AVClub1Benzinga1BikeRadar1Billboard1BloodyDisgusting1Borderlands1Bungie1Yahoo!FinanceCanada1CineD1CnEVPost1comicbook1CreativeBloq1CyberSecurityNews1DailyKos1DCRainmaker1derekthompson1Draftsim1CNN1flatpanelshd1FratelloWatches1FrequentMiler1GAMINGbible1garymarcus.substack1GeekWire1GeekyGadgets1Hackaday1HollywoodReporter1InsiderGaming1InterconnectsAI1InterestingEngineering1JapanTimes1KrebsonSecurity1KSL1LosAngelesTimes1Lloyd'sList1WPLGLocal101Macworld1Maxroll1Mediaite1MiddleEastEye1MonochromeWatches1MortgageDaily1MP1st1MPR1SemiAnalysis1Newsshooter1NoMan'sSky1nylon.com.sg1NYT1OregonLive1PCGamesN1PersonaCentral1Pokemon1politico.eu1PittsburghPost-Gazette1QuantaMagazine1qz1SammyGuru1ScienceAlert1ScientificAmerican1SouthChinaMorningPost1Semafor1SFGATE1YahooFinanceSingapore1YahooSingapore1SportsIllustrated1SimpleFlying1Sources1supercarblondie1Tedium1TelecomTalk1GameBusiness1TheGamer1Times1LongmontTimes-Call1TmoNews1TopGear1TwistedVoxel1YahooFinanceUK1UnHerd1vox1WhatHi-Fi?1WPBF1WRAL1
  1. 001Hacker NewsSEP · 16English

    I Put Nam A2-Lite Inside an iRig HD X

    A developer integrated NAM A2-Lite, a compact neural amp model, directly into an iRig HD X audio interface by repurposing its NXP Cortex-M7 microcontroller. The guitar signal now runs through amp modeling on the device itself at 48 kHz, eliminating the need for external computers while maintaining real-time performance within tight memory and processing constraints.

    By arbayi
  2. 002Hacker NewsSEP · 16English

    Categorize Everything All at Once

    A developer discusses using regex for named entity recognition and categorization tasks. They demonstrate how regex patterns can efficiently handle tasks like date validation, email detection, and money recognition, comparing favorably to neural network approaches while using far fewer computational resources. The post showcases regex expressivity through composable patterns and finite state machines.

    By Ian Erik Varatalu
  3. 003Hacker NewsSEP · 16English

    Show HN: MinMAX Sort – A Stable Bidirectional Selection Sort Family Algorithm

    A developer created MinMAX Sort, a stable bidirectional selection sort variant that reduces operations by approximately half compared to traditional selection sort through optimizations to both outer and inner loops. The algorithm has been tested extensively on various array patterns and arrangements.

    By jodenghog
  4. 004Hacker NewsSEP · 16English

    SGLang and Miles Add Day-0 Support for DeepSeek-v4.1

    SGLang and Miles add day-0 support for DeepSeek-V4.1, a model featuring low-ratio compression, sliding-window attention, manifold hyper-connections, and Engram memory for efficient serving. The implementation includes cross-layer sharing, sparse retrieval mechanisms, and host-memory placement optimizations that increase KV cache capacity by 36% while maintaining comparable throughput.

    By SGLang; Miles Teams
  5. 005Hacker NewsSEP · 16English

    Deep Seek v4.1 M5 Max at 17 tokens/s

    Deep Seek v4.1 M5 Max achieves 17 tokens/s by optimizing mixture-of-experts model execution from SSDs on a 128GB laptop. The system reads only routed experts (187 of 384 per layer) instead of all experts, achieving 1.73× speedup on prefill; adding multiple drives reduces read latency rather than increasing bandwidth, with time-to-first-token improving from 31.5s (baseline) to 18.3s (one drive) to 11.7s (three drives).

    By Argonautlabsai
  6. 006Hacker NewsSEP · 16English

    We cut CDN metadata lookup latency by 91%

    Vercel reduced CDN metadata lookup latency by 91% by grouping path metadata into shards instead of fetching individual paths. The optimization batches metadata fetches together while using indexed shards to avoid unnecessary parsing, balancing efficiency gains against data transfer costs.

    By Tim Caswell
  7. 007Hacker NewsSEP · 15English

    A New Experiment Meta-Strategy (and my shiny new lab!)

    A researcher reorganized their home lab to remove friction from experimental work, then created a Claude-powered app that generates experiment ideas based on their existing equipment inventory, ranking them by difficulty and setup time while prioritizing novel phenomena amenable to independent science.

    By CasualPhysicsEnjoyer
  8. 008Hacker NewsSEP · 15English

    Open-Source Skill Makes Claude Code 38% Cheaper and 38% Faster on Small Projects

    Product Traceability 2.0, an open-source skill for Claude Code, achieved 38% cost reduction and 38% faster build times on small projects by moving product history maintenance out of the coding agent's loop. Version 1.0 failed because it required the agent to maintain four Markdown files synchronously, consuming excessive compute; Version 2.0 separates coding work from record-keeping to preserve efficiency.

    By Vlad Mysla
  9. 009Hacker NewsSEP · 15English

    Is Compounding Inference as Powerful as Compounding Interest?

    Shopify's ML team demonstrated compounding inference by fine-tuning a 0.8B-parameter model that outperformed GPT-5.6-sol on buyer profile tasks through three rapid training cycles in one week. The breakthrough came from reinvesting inference outputs as training data, reducing prompt costs 8x, and increasing throughput 36x across three simultaneous feedback loops. Success required task-specific quality judges, production-to-training data pipelines, rapid iteration cadence, and dynamic routing between teacher and student models.

    By Rob May
  10. 010Hacker NewsSEP · 15English

    Show HN: Self-adjusting vLLM at production scale

    Rivvr automates vLLM deployment at production scale by automatically tuning configurations, monitoring metrics, and adjusting cluster topology to maintain latency and throughput SLO targets while reducing AWS costs by 40-70%.

    By dmitriisn
  11. 011Hacker NewsSEP · 15English

    Show HN: Go Bindings for SCIP Optimizer

    scipgo provides Go bindings for SCIP, a high-performance mixed integer programming solver, offering a stable API with support for various constraint types, pluggable solvers, and concurrent solving capabilities. The library emphasizes safety through stage checking and error handling, integrates with Go contexts and logging, and includes comprehensive documentation with eleven example programs.

    By Egoisutolabs
  12. 012Hacker NewsSEP · 15English

    Show HN: Warp – Run DeepSeek v4.1 Flash with 5 GB of RAM at 3.77 tok/s

    WARP is a C-based inference engine that runs large language models on consumer hardware by keeping model trunks in RAM and streaming experts from disk. It successfully runs DeepSeek-V4.1-Flash at 3.77 tokens per second on 5 GB RAM and Kimi K3 at 0.6 tokens per second on a 64 GB MacBook Pro using mixture-of-experts architecture and optimized disk I/O.

    By Sqliteai