[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"article-why-databricks-model-serving-is-right-default-zh":3,"tags-why-databricks-model-serving-is-right-default-zh":38,"related-lang-why-databricks-model-serving-is-right-default-zh":47,"related-posts-why-databricks-model-serving-is-right-default-zh":51,"series-tools-4adef3ab-9f07-4970-91cf-77b8b581b348":88},{"id":4,"title":5,"content":6,"summary":7,"source":8,"source_url":9,"author":10,"image_url":11,"keywords":12,"language":19,"translated_content":10,"views":20,"is_premium":21,"created_at":22,"updated_at":22,"cover_image":11,"published_at":23,"rewrite_status":24,"rewrite_error":10,"rewritten_from_id":25,"slug":26,"category":27,"related_article_id":28,"status":29,"google_indexed_at":30,"x_posted_at":10,"tweet_text":10,"title_rewritten_at":10,"title_original":10,"key_takeaways":31,"topic_cluster_id":35,"embedding":36,"is_canonical_seed":37},"4adef3ab-9f07-4970-91cf-77b8b581b348","為什麼 Databricks Model Serving 是生產推論的正確預設","\u003Cp data-speakable=\"summary\">Databricks Model Serv\u003Ca href=\"\u002Fnews\u002Fwhy-xiaomi-mimo-v25-pro-changes-coding-agents-zh\">ing\u003C\u002Fa> 應該是生產推論的預設選項，因為它把部署、治理與擴展整合在同一個平台。\u003C\u002Fp>\u003Cp>我支持把 Databricks Model Serving 當作生產推論的預設選項，因為真正的成本不在第一個 endpoint，而在後續長出來的基礎設施、權限、監控與維運分歧。它同時支援自建 MLflow 模型、foundation model 與外部 \u003Ca href=\"\u002Ftag\u002Fllm\">LLM\u003C\u002Fa>，還提供單一 REST \u003Ca href=\"\u002Ftag\u002Fapi\">API\u003C\u002Fa>、單一介面、serverless autoscaling 與內建治理。對要把模型真正送進產品的團隊來說，這不是「方便」而已，而是少走一整套平台重建的路。\u003C\u002Fp>\u003Ch2>第一個論點：一個平台勝過拼湊式模型堆疊\u003C\u002Fh2>\u003Cp>Model Serving 最強的價值是整合。Databricks 讓團隊用同一個 serving layer 管理自建模型、託管 foundation model 和外部模型，等於把三套營運模式收斂成一套。你可以先把 MLflow 模型註冊到 Unity Catalog，再用 REST endpoint 對外提供服務，之後也能把 GPT-4 這類外部模型納入同一套治理面。少的是工具數量，多的是穩定性。\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778692245329-a2wt.png\" alt=\"為什麼 Databricks Model Serving 是生產推論的正確預設\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>這在從 PoC 走向 production 時最明顯。概念驗證可以接受腳本、臨時 wrapper、單點部署；生產系統不行。當產品、分析、ML 團隊都要共用模型能力時，統一 serving layer 會直接降低整合成本。Databricks 連 AI Functions 和 ai-query 的 batch inference 都能從 SQL 直接做，對已經把資料管線放在 warehouse 的公司來說，這代表資料、模型、應用之間少了一段手工搬運。\u003C\u002Fp>\u003Ch2>第二個論點：治理不是附加功能，而是產品本體\u003C\u002Fh2>\u003Cp>Model Serving 之所以值得當預設，不是因為它只會 host 模型，而是它把治理放到第一層。Serving UI 集中管理權限、用量限制與監控，連外部託管的 endpoint 也能納入同一個控制面。對企業來說，這很重要，因為最常見的失敗不是模型不準，而是權限散落、政策不一致、部門各自接 API。Databricks 透過 AI \u003Ca href=\"\u002Fnews\u002Fgala-games-web3-gaming-2026-zh\">Ga\u003C\u002Fa>teway 把這些東西收斂到單一 control plane，降低治理碎片化。\u003C\u002Fp>\u003Cp>安全性也不是口號，而是能落地的操作條件。請求會被隔離、驗證與授權，資料靜態加密採 AES-256，傳輸中加密採 TLS 1.2+；付費帳號的輸入與輸出不會被拿去訓練 Databricks 服務。這些不是加分題，而是企業能不能放行內部模型服務的基本門檻。再加上 serverless egress control 的網路政策，安全團隊才有真正能執行的槓桿，而不是紙上規範。\u003C\u002Fp>\u003Ch2>第三個論點：生產推論要擴展，更要穩定\u003C\u002Fh2>\u003Cp>autoscaling 和低延遲只有在真實負載下穩定才有意義，而這正是 Model Serving 的定位。Databricks 公開說明其服務可支援超過 25K QPS，且 overhead latency 低於 50 ms。不是每個團隊都需要這個數字，但平台設計本身已經朝高可用 production 走，而不是只滿足 demo。serverless compute 也讓流量變化不必再卡在基礎設施排程上。\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778692269106-4a4z.png\" alt=\"為什麼 Databricks Model Serving 是生產推論的正確預設\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>另一個很能看出成熟度的細節，是 Databricks 不會直接在原有 model image 上打補丁。新版本模型會建立帶有最新 patch 的新 image，但舊 image 會保留不動，避免影響線上部署。這個取捨是對的。生產推論不是桌面軟體更新，不能為了「永遠最新」去犧牲線上穩定。對 live endpoint 來說，避免中斷的價值遠高於強迫立即升版。\u003C\u002Fp>\u003Ch2>反方可能怎麼說\u003C\u002Fh2>\u003Cp>最強的反對意見是，Model Serving 把太多東西集中在同一個平台，容易讓團隊依賴單一供應商的抽象層、定價與限制。這個擔心合理。若公司只需要一個簡單 c\u003Ca href=\"\u002Fnews\u002Fwhy-rust-is-the-ai-language-of-the-future-zh\">ust\u003C\u002Fa>om model API，較輕量的部署方式確實可能更便宜、更容易理解。另一個風險是，managed serving 可能讓團隊推得太快，卻還沒準備好對應的治理流程，尤其當內部模型和外部 LLM 開始混用時。\u003C\u002Fp>\u003Cp>也有人會說，managed serving 只是把複雜度藏起來，不是真的消除它。autoscaling、throughput tuning、model versioning、region constraint、endpoint limit 這些問題都還在。如果團隊要的是對 runtime、networking、image lifecycle 的絕對控制，自己維護 serving stack 會更合適。從這個角度看，Databricks 不是所有部署問題的答案，它是處理「多模型、多團隊、強治理」這類問題的強答案。\u003C\u002Fp>\u003Cp>但這個反方論點沒有推翻它，只是劃出邊界。當問題是組織規模，而不是玩具級簡單部署時，Model Serving 就是正確預設。只要公司需要一個政策面來管多種模型、一個可擴展的 endpoint 模型、以及一個能看見存取與成本的地方，managed approach 就會贏。供應商綁定是真實代價，但把 hosting、auth、scaling、monitoring 拆成多套工具的營運債也同樣真實，而且在 production 裡增長更快。\u003C\u002Fp>\u003Ch2>你能做什麼\u003C\u002Fh2>\u003Cp>如果你是工程師，當團隊需要快速上線、受管存取、以及支援多種模型型態時，把 Model Serving 當成生產推論的基準方案。如果你是 PM，從第一天就把權限、用量限制、成本可視化與版本管理納入 serving 策略，不要等上線後再補。如果你是創辦人，請優先設計你在十個模型、三個團隊下要怎麼營運，而不是只看第一個 demo 的成本。真正的問題不是能不能自己 host 模型，而是你願不願意自己承擔安全地大規模營運它的全部責任。\u003C\u002Fp>","Databricks Model Serving 應該成為生產推論的預設選項，因為它把部署、治理與擴展整合在同一個平台，降低多模型團隊的營運成本。","docs.databricks.com","https:\u002F\u002Fdocs.databricks.com\u002Faws\u002Fen\u002Fmachine-learning\u002Fmodel-serving\u002F",null,"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778692245329-a2wt.png",[13,14,15,16,17,18],"Databricks","Model Serving","production inference","governance","autoscaling","Unity Catalog","zh",0,false,"2026-05-13T17:10:30.659153+00:00","2026-05-13T17:10:30.443+00:00","done","756274c8-9156-48a2-b3f8-eeff2b630b6a","why-databricks-model-serving-is-right-default-zh","tools","1f1bff1e-0ebc-4fa7-a078-64dc4b552548","published","2026-05-14T09:00:17.706+00:00",[32,33,34],"Databricks Model Serving 的核心優勢是把部署、治理與擴展收斂到同一個平台。","它特別適合作為多模型、多團隊、強治理場景下的生產推論預設。","反對意見成立於小型簡單部署，但不足以否定它在企業規模下的優勢。","6d7e007a-da26-455a-af52-fcbe1ddc66a0","[-0.022891263,0.01279158,0.03709723,-0.08898913,-0.015725888,-0.017526058,0.0031490484,0.027458949,0.03756907,0.021431193,-0.010739585,-0.016836915,0.011137425,0.013933341,0.13552986,0.019760098,0.030659648,-0.01787489,0.012488583,0.025584802,0.016974857,0.015909225,-0.022572795,0.01450725,0.0035278772,-0.002047413,0.035153516,0.0003527429,0.018340476,-0.025670182,0.013521425,0.0034881695,0.018622465,0.030797184,0.008396097,0.0010284958,-0.01020147,-0.023123601,0.029563256,0.024490539,-0.007036337,0.009561841,0.0030851744,-0.026306916,-0.016909003,0.0044598025,0.022104243,-0.03551124,0.011380252,-0.015730098,0.016295947,0.0021773821,-0.0015447568,-0.14403066,-0.004428624,0.011930107,-0.0069827517,0.007773119,0.0010026381,0.0078364285,0.0152948275,0.032604203,-0.012054084,-0.00722196,0.011039291,0.00053937413,0.023784054,0.0053433366,0.03464387,-0.012985435,-0.0015121107,0.012778854,0.008711486,-0.030748919,0.022778677,-0.021645676,-0.0051768757,-0.02596978,-0.009837783,0.0036624025,0.0122571755,-0.04122714,0.020081284,-0.014151334,-0.028983226,0.064270176,0.01791912,-0.006604079,0.0009917726,0.018668344,0.03147976,-0.008239798,-0.0031007018,0.026772652,-0.014493153,-0.00956137,0.0092750285,-0.03227139,0.004300078,-0.023205215,-0.013085065,0.011981206,-0.0017336938,0.0142166875,-0.009798014,0.015753642,0.005015327,-0.0008019619,-0.008185248,0.014355211,0.0056335605,-0.0061175614,0.013519429,0.004931456,0.007901013,-0.119211726,0.017922375,-0.013040599,0.008964867,0.004240893,-0.03298349,-0.011660836,-0.006537126,0.026339922,-0.0016160217,0.0138886,0.00351284,0.02820138,-0.012047968,-0.009259541,0.0023474807,-0.018714786,-0.041174885,0.02512431,-0.011126718,0.014086552,0.0020024553,0.0037377998,-0.026532512,-0.030662898,-0.014798726,0.017625242,0.00551455,-0.0019861648,-0.019558642,0.0059542623,-0.041606084,0.019972214,0.008513487,0.0078968415,0.0028294888,-0.002291344,0.002551765,-0.0041616154,0.015918223,-0.0009353324,0.0068281707,-0.011656911,0.011535226,0.03134001,-0.008713485,-0.011562234,-0.014849185,0.013751444,0.012853306,0.008885445,0.0048799925,0.016521832,0.0052982178,0.009179708,0.021939306,0.011649859,-0.018593509,0.021761708,-0.0100896405,0.011905737,-0.00517776,4.7343274e-05,0.012844646,-0.042678796,0.027680133,-0.015236927,-0.020664807,-0.0060525644,-0.023611246,-0.0153669175,-0.0052646575,0.004920013,0.016273614,0.0051767267,0.0042786733,0.005727225,-0.0047253035,-0.003933389,-0.009655434,-0.0044220234,0.018521145,-0.004841039,-0.0014274139,0.006044269,0.0069084894,-0.030076604,0.0069393483,-0.033047743,-0.0013202479,-0.026548546,0.003390447,-0.017033665,0.0037508428,0.0012516679,-0.023586106,-0.0030986248,0.016832426,0.0062675066,0.008023348,-0.016410906,-0.019336702,-0.0064438605,0.0076113227,-0.013565259,0.031835843,-0.007652797,-0.012691389,0.014428726,-0.021049442,-0.02614673,0.00641924,-0.01670197,-0.022590667,-0.008368766,0.02412257,-0.012020323,0.02257923,0.001980939,0.011109926,-0.028126169,0.0033510795,0.006234991,-0.001760024,0.03505045,-0.007407261,0.020286385,0.00025872706,-0.014502119,-0.0011387005,-0.015396158,-0.0048121708,-0.021154901,-0.027526725,0.020629581,-0.00037217,-0.016927743,0.016138425,0.0020075953,0.03289977,-0.01622627,-0.03257776,0.027375933,0.018912697,0.015460784,-0.001134641,-0.012205541,0.012887714,-0.024804167,0.015477844,0.009757218,0.01868578,-0.0068405624,-0.028405758,0.016902216,-0.004047248,-0.0074796597,-0.023517473,0.016745077,0.015195418,-0.004377159,-0.016421858,0.0100274775,-0.005235987,-0.01761493,-0.024957553,0.008737671,-0.0055843215,0.018796459,0.00010622666,0.0096498765,-0.014116458,0.004213237,-0.018675731,0.008177342,-0.0064926716,0.025674932,-0.029393326,-0.00984924,0.027898002,-0.020600757,-0.021867039,0.014507391,0.016007513,0.010683211,-0.01570644,-0.00014803212,0.00400766,0.059777956,-0.029585835,0.018023394,0.025932968,-0.00095292996,-0.019679435,-0.011654032,-0.008497488,-0.015579051,0.010845152,0.0036748576,-0.029559495,0.013627903,0.024774952,-0.016356558,-0.008849174,0.0060257944,-0.0029672843,0.012513475,-0.020906307,0.02276639,-0.02078321,0.008983072,0.018694757,0.0005559758,0.0027304634,-0.0153673515,0.0034108965,-0.027957713,0.010938711,-0.03198978,-0.014294279,0.01139682,-0.019198943,-0.0030031172,-0.024936562,0.028107306,0.007453599,-0.012415899,-0.030300884,-0.026673408,-0.01591821,0.0012488228,0.041107953,0.006750459,0.028144192,0.0019509563,0.04738583,-0.009683739,0.0047459775,-0.0070555517,-0.0142859835,0.00769048,-0.008398832,-0.0037681658,0.038693264,-0.005085468,0.011742237,-0.026614279,-0.042634435,-0.009683894,0.005296356,0.002979866,-0.01665935,0.009324896,0.006982825,-0.019407794,0.005800372,0.020218749,0.018593853,0.006403178,0.0071890205,-0.008281523,-0.00047226655,-0.025453815,-0.004834855,0.0056988127,-0.0038527288,0.013683552,-0.0039944416,-0.013166589,-0.009651397,-0.009334393,0.04542003,0.020764459,-0.027621463,0.0043398207,-0.0009766072,-0.009924721,0.00025318787,-0.0094846245,-0.009467526,-0.012807146,-0.020610312,0.011252583,-0.022402175,-0.030601783,0.0031116798,-0.009803661,-0.011059968,-0.010182357,-0.0098462235,0.004960406,-0.018190265,0.0068086335,0.0076482594,0.0028814347,0.004016363,-0.006680251,-0.008450759,-0.004167613,0.015175661,-0.003947429,-0.0049552685,0.012720693,-0.00067805004,-0.009893862,0.0010706612,-0.015825491,0.009882155,-0.013389397,-0.009759014,-0.00072180637,-0.013469714,0.0089226095,-0.012604374,-0.012060582,0.016221838,-0.0049989237,-0.0003620387,-0.0040030107,-0.017935457,-0.008612186,-0.027653012,-0.0003360463,-0.017490638,-0.03485231,0.01891908,0.005320706,0.008526395,-0.025171125,0.0032659883,0.009044181,-0.0029783987,-0.011619008,-0.0115062455,-0.00083516317,0.010029993,0.046443515,0.017125012,-0.018239142,-0.0020234433,0.002447971,-0.015086833,0.024830785,0.0044251983,-0.0020185194,-0.012164211,0.014855306,0.021238508,-0.008062633,0.008590568,0.0017815614,-0.0080749765,-0.013649729,0.016389478,-0.005706073,-0.010527794,0.0008134046,0.016104676,0.005694012,-0.007880596,-0.01695688,0.039998524,0.0062839068,0.0053104605,0.031466737,0.036272693,-0.031522814,0.019019032,0.010669129,-0.016394753,0.0076557575,-0.012641322,0.0131437015,-0.013198847,-0.008702186,0.00424693,0.03544748,-0.005535718,-0.0039663767,-0.01501104,0.0077169263,-0.0071018003,0.005494071,0.037576437,-0.0032330055,-0.02622989,0.02785949,-0.008808692,-0.012277374,0.01746808,-0.010478968,0.021841995,0.008245626,-0.017717833,-0.00069571886,-0.035366304,-0.011448028,0.00880817,0.009545581,0.010012682,-0.014266736,-0.01245454,-0.009792641,-0.052117053,0.013902741,0.020097034,-0.030021854,-0.009980132,0.0060608354,-0.012199158,0.012836105,0.007327738,0.013692447,0.0413258,0.03400878,-0.019446628,0.012467404,0.00014349793,-0.010308445,0.0009315013,-0.009378159,-0.0036908311,0.024177494,-0.00051523274,-0.0061388095,-0.0021038624,-0.004081605,-0.0069153463,0.007032775,-0.0007938587,-0.07759141,0.0069360584,-0.015498516,-0.008736014,0.0248802,-0.017453935,-0.029346466,-0.013559343,0.0037329774,-0.0224594,0.005999438,-0.01705486,-0.0027125513,-0.0068490067,-0.007831542,-0.016746135,-0.0042583616,-0.012993814,0.02255887,-0.009468786,0.031182071,0.012582016,0.0013596796,0.032445576,0.0016466209,-0.00039982708,-0.032120723,0.0052248524,0.0062629743,-0.006585941,-0.018575177,-0.021775598,0.024345443,0.0007580201,0.007600978,-0.0035154663,-0.0006115639,-0.013540164,0.034374077,0.0076207034,0.022023264,0.0029469512,-0.029846558,-0.017436393,0.01757941,0.011442407,0.012352301,-0.018855378,0.03139666,0.0056147315,-0.010004705,-0.028447913,-0.004783925,-0.016422816,-0.019176513,0.01039209,-0.0037717754,0.006373355,0.016156647,0.004146188,-0.005627852,-0.010815156,-0.028168678,0.019664451,-0.039042577,-0.032014627,-0.0015313553,0.022021897,0.010182968,0.023166506,0.0003599244,-0.013942973,-0.027518868,-0.021073127,0.024028763,0.013034913,-0.016901173,0.032463737,0.035705302,-0.024930581,-0.03808608,0.020930337,-0.08302701,-0.04295634,-0.021876387,0.0058851545,0.018528918,-0.00016380826,-0.0014073631,-0.0113906395,-0.0051665897,-0.0023056464,0.0036181028,-0.023393746,0.016878735,-0.009013999,0.0061602527,0.02316221,0.02201206,0.023737395,-0.00082240824,-0.03509838,0.029670712,-0.026528722,0.009126295,-0.013980263,-0.02113696,0.0048217,-0.004055993,-0.004707951,-0.0033351923,-0.021047512,-0.0193125,-0.14246862,0.010181273,-0.001302624,0.007483518,-0.00687162,0.027686706,-0.008251945,-0.017490191,-0.017411051,-0.010477936,-0.0089444285,-0.025734326,-0.032866314,-0.00076868624,-0.019305918,0.12429574,-0.011642601,-0.0007375053,0.009372578,-0.015722273,-0.015680742,-0.0076476224,0.01918974,0.001782694,0.016169664,0.00577057,0.007266637,0.01320537,-0.01668989,0.02045729,-0.0025710368,0.011283907,-0.019255161,-0.034669265,0.009240957,-0.017624773,-0.019863691,-0.016614338,0.025300661,0.003157714,-0.009167047,0.009778812,0.009816283,0.011494208,-0.007272737,0.0021263876,-0.027898422,-0.008835442,0.017511882,-0.019055292,-0.043482706,-0.07251049,-0.000115840136,0.014796448,-0.007467499,0.016907832,0.006113646,0.02746317,0.00012163741,-0.014487798,0.02866236,0.028648194,0.04556346,0.03273804,-0.0067019886,0.023771774,0.04279171,0.05771973,-0.0018509913,0.008804504,-0.017463522,0.0032731248,-0.0028867824,-0.019386128,-0.009827381,-0.012317383,0.02523189,0.022741402,0.026760207,-0.013745859,0.0038999154,0.013927897,-0.007298605,-0.034497287,-0.028400267,-0.0030113112,0.034378067,-0.008677744,-0.0065978942,-0.021564415,0.006633034,0.040784396,0.011494559,0.019751435,0.02235427,-0.022117928,-0.02752365,0.023427742,0.031823892,-0.015024251,0.020224515,-0.017730543,0.024618065,0.0030634552,-0.016708685,0.012544502,0.0028583454,0.019145105,0.0070127607,-0.010649566]",true,[39,41,42,43,45],{"name":14,"slug":40},"model-serving",{"name":17,"slug":17},{"name":16,"slug":16},{"name":13,"slug":44},"databricks",{"name":15,"slug":46},"production-inference",{"id":28,"slug":48,"title":49,"language":50},"why-databricks-model-serving-is-right-default-en","Why Databricks Model Serving is the right default for production infe…","en",[52,58,64,70,76,82],{"id":53,"slug":54,"title":55,"cover_image":56,"image_url":56,"created_at":57,"category":27},"68e4be16-dc38-4524-a6ea-5ebe22a6c4fb","why-vidhub-huiyuan-hutong-bushi-quan-shebei-tongyong-zh","為什麼 VidHub 會員互通不是「買一次全設備通用」","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778789450987-advz.png","2026-05-14T20:10:24.048988+00:00",{"id":59,"slug":60,"title":61,"cover_image":62,"image_url":62,"created_at":63,"category":27},"7a1e174f-746b-4e82-a0e3-b2475ab39747","why-buns-zig-to-rust-experiment-is-right-zh","為什麼 Bun 的 Zig-to-Rust 實驗是對的","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778767879127-5dna.png","2026-05-14T14:10:26.886397+00:00",{"id":65,"slug":66,"title":67,"cover_image":68,"image_url":68,"created_at":69,"category":27},"e742fc73-5a65-4db3-ad17-88c99262ceb7","why-openai-api-pricing-is-product-strategy-zh","為什麼 OpenAI API 定價是產品策略，不是註腳","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778749859485-chvz.png","2026-05-14T09:10:26.003818+00:00",{"id":71,"slug":72,"title":73,"cover_image":74,"image_url":74,"created_at":75,"category":27},"c757c5d8-eda9-45dc-9020-4b002f4d6237","why-claude-code-prompt-design-beats-ide-copilots-zh","為什麼 Claude Code 的提示設計贏過 IDE Copilot","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778742645084-dao9.png","2026-05-14T07:10:29.371901+00:00",{"id":77,"slug":78,"title":79,"cover_image":80,"image_url":80,"created_at":81,"category":27},"b3305057-451d-48e4-9fb9-69215f7effad","why-ibm-bob-right-kind-ai-coding-assistant-zh","為什麼 IBM 的 Bob 才是對的 AI 寫碼助手","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778664653510-64hc.png","2026-05-13T09:30:21.881547+00:00",{"id":83,"slug":84,"title":85,"cover_image":86,"image_url":86,"created_at":87,"category":27},"c263e0ea-d6ab-41e9-86cb-c4484a4d3621","why-mvm-is-the-right-kind-of-go-interpreter-zh","為什麼 Mvm 才是正確的 Go Interpreter","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778573459130-is3c.png","2026-05-12T08:10:24.323293+00:00",[89,94,99,104,109,114,119,124,129,134],{"id":90,"slug":91,"title":92,"created_at":93},"de769291-4574-4c46-a76d-772bd99e6ec9","googles-biggest-gemini-launches-in-2026-zh","Google 2026 最大 Gemini 盤點","2026-03-26T07:26:39.21072+00:00",{"id":95,"slug":96,"title":97,"created_at":98},"855cd52f-6fab-46cc-a7c1-42195e8a0de4","surepath-real-time-mcp-policy-controls-zh","SurePath 推出即時 MCP 政策控管","2026-03-26T07:57:40.77233+00:00",{"id":100,"slug":101,"title":102,"created_at":103},"9b19ab54-edef-4dbd-9ce4-a51e4bae4ebb","mcp-in-2026-the-ai-tool-layer-teams-use-zh","2026 年 MCP：團隊真的在用的 AI 工具層","2026-03-26T08:01:46.589694+00:00",{"id":105,"slug":106,"title":107,"created_at":108},"af9c46c3-7a28-410b-9f04-32b3de30a68c","prompting-in-2026-what-actually-works-zh","2026 提示工程，真正有用的是什麼","2026-03-26T08:08:12.453028+00:00",{"id":110,"slug":111,"title":112,"created_at":113},"05553086-6ed0-4758-81fd-6cab24b575e0","garry-tan-open-sources-claude-code-toolkit-zh","Garry Tan 開源 Claude Code 工具包","2026-03-26T08:26:20.068737+00:00",{"id":115,"slug":116,"title":117,"created_at":118},"042a73a2-18a2-433d-9e8f-9802b9559aac","github-ai-projects-to-watch-in-2026-zh","2026 必看 20 個 GitHub AI 專案","2026-03-26T08:28:09.619964+00:00",{"id":120,"slug":121,"title":122,"created_at":123},"a5f94120-ac0d-4483-9a8b-63590071ac6a","claude-code-vs-cursor-2026-zh","Claude Code 與 Cursor 深度對比：202…","2026-03-26T13:27:14.279193+00:00",{"id":125,"slug":126,"title":127,"created_at":128},"0975afa1-e0c7-4130-a20d-d890eaed995e","practical-github-guide-learning-ml-2026-zh","2026 機器學習入門 GitHub 實用指南","2026-03-27T01:16:49.712576+00:00",{"id":130,"slug":131,"title":132,"created_at":133},"bfdb467a-290f-4a80-b3a9-6f081afb6dff","aiml-2026-student-ai-ml-lab-repo-review-zh","AIML-2026：像課綱的學生實驗 Repo","2026-03-27T01:21:51.467798+00:00",{"id":135,"slug":136,"title":137,"created_at":138},"80cabc3e-09fc-4ff5-8f07-b8d68f5ae545","ai-trending-github-repos-and-research-feeds-zh","AI Trending：把 AI 資源收成一張表","2026-03-27T01:31:35.262183+00:00"]