[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"article-weishenme-fensanshi-xitong-yanjiang-bi-buluoge-wenzhang-geng-zh":3,"article-related-weishenme-fensanshi-xitong-yanjiang-bi-buluoge-wenzhang-geng-zh":35,"series-research-e3f8d32d-9094-4717-b9fd-d799de0e521b":83},{"id":4,"title":5,"content":6,"summary":7,"source":8,"source_url":9,"author":10,"image_url":11,"keywords":12,"language":18,"translated_content":10,"views":19,"is_premium":20,"created_at":21,"updated_at":21,"cover_image":11,"published_at":22,"rewrite_status":23,"rewrite_error":10,"rewritten_from_id":24,"slug":25,"category":26,"related_article_id":27,"status":28,"google_indexed_at":10,"x_posted_at":10,"tweet_text":10,"title_rewritten_at":10,"title_original":10,"key_takeaways":29,"topic_cluster_id":33,"embedding":34,"is_canonical_seed":20},"e3f8d32d-9094-4717-b9fd-d799de0e521b","為什麼分散式系統演講比部落格文章更值得學","\u003Cp data-speakable=\"summary\">\u003Ca href=\"\u002Ftag\u002F分散式系統\">分散式系統\u003C\u002Fa>演講比部落格文章更能快速學到真實取捨，因為它們把理論、故障與生產經驗放在同一條脈絡裡。\u003C\u002Fp>\u003Cp>如果你想真正理解分散式系統，先看演講，別先追逐包裝過的部落格摘要。從 Martin Kleppmann 的 Cambridge lectures，到 Netflix 的流量暴增與有狀態系統案例，再到 \u003Ca href=\"\u002Fnews\u002Fclaude-code-v2-1-143-background-session-fixes-zh\">Cl\u003C\u002Fa>oudflare 的 Kafka 經驗、Duolingo 的 Super Bowl 通知故事，這份清單本身就說明了一件事：這門領域最有價值的知識，通常不是被寫成漂亮文章，而是被講成失敗、權衡與修正。\u003C\u002Fp>\u003Ch2>第一個論點\u003C\u002Fh2>\u003Cp>演講比文字更擅長壓縮艱難得來的營運知識。Kleppmann 的八堂課把 replication、consistency、consensus 這些概念按學習路徑排好，而不是丟給你一堆零散搜尋結果。對初學者來說，這種結構能把理解時間從「幾週拼湊」縮短成「一個系列看完」，差異非常直接。\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779075234067-fff9.png\" alt=\"為什麼分散式系統演講比部落格文章更值得學\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>企業案例更能證明這點。Netflix 的「How Netflix Handles Sudden Load Spikes in the Cloud」與「How Netflix Ensures Highly-Reliable Online Stateful Systems」不是泛泛而談的最佳實踐，而是把流量暴增、狀態管理、延遲與成本放在同一個決策框架裡。你從演講裡看到的是具體故障與修法，不是被修飾過的結論。\u003C\u002Fp>\u003Ch2>第二個論點\u003C\u002Fh2>\u003Cp>分散式系統最難學的地方，不是名詞，而是失敗模式。\u003Ca href=\"\u002Ftag\u002Fcloudflare\">Cloudflare\u003C\u002Fa> 的「Lessons Learnt on the Way to 1 Trillion Messages」與 Duolingo 的「Delivering Millions of Notifications within Seconds During the Super Bowl」之所以重要，是因為它們直接展示了規模一上來後，吞吐、ba\u003Ca href=\"\u002Fnews\u002Ferock-files-nyse-ipo-power-demand-zh\">ck\u003C\u002Fa>pressure、可靠性如何把原本看似合理的設計打回原形。\u003C\u002Fp>\u003Cp>同樣地，像「Complexity is the Gotcha of Event-driven Architecture」和「How Event Driven Architectures Go Wrong & How to Fix Them」這類演講，價值在於它們不把 event-driven architecture 當口號，而是當成風險來源。當團隊先上 Kafka、microservices、saga，後補營運能力時，最缺的正是這種把坑講清楚的內容。資料顯示，系統越複雜，事故成本越高，越需要先理解失敗再談設計。\u003C\u002Fp>\u003Ch2>反方可能怎麼說\u003C\u002Fh2>\u003Cp>最強的反對意見很簡單：演講是被動吸收，耗時又容易讓人產生「我懂了」的錯覺。部落格文章、文件與程式碼範例，往往更適合直接查答案，尤其當工程師現在就要解一個 replication bug、一次 timeout 或一個 retry 策略時，長影片不一定比短文有效。\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779075230760-rhat.png\" alt=\"為什麼分散式系統演講比部落格文章更值得學\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>這個批評是成立的，而且它指出了演講的限制：看懂不等於做得出來。演講不能取代動手實作，也不能自動補上你在生產環境裡要面對的監控、除錯與維運壓力。\u003C\u002Fp>\u003Cp>但這不表示演講不值得看，而是表示你要把它放在正確的位置。先用演講建立失敗、取捨與規模的心智模型，再去看文件、寫程式、做實驗，學習效率會高得多。分散式系統最貴的學費不是看錯一篇文章，而是在 production 裡才第一次理解你沒想到的邊界條件。\u003C\u002Fp>\u003Ch2>你能做什麼\u003C\u002Fh2>\u003Cp>如果你是工程師，把這類清單當課綱，不要當播放清單。先看基礎演講，再挑一個和你工作場景最接近的案例，最後補一支你最怕的失敗模式演講。每看完一支，記下三件事：它解決了\u003Ca href=\"\u002Fnews\u002Fcommunity-resistance-will-reshape-ai-data-center-expansion-zh\">什麼\u003C\u002Fa>故障、用了哪些指標、犧牲了什麼取捨。如果你是 PM 或創辦人，請用這些演講校準產品決策，因為每一個看似簡單的分散式功能，背後都藏著延遲、可觀測性、重試、狀態與支援成本。先建立判斷力，再把系統推上線，通常比事後補救便宜得多。\u003C\u002Fp>","分散式系統演講比部落格文章更能快速學到真實取捨，因為它們把理論、故障與生產經驗放在同一條脈絡裡。","www.techtalksweekly.io","https:\u002F\u002Fwww.techtalksweekly.io\u002Fp\u002F30-best-distributed-systems-talks",null,"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779075234067-fff9.png",[13,14,15,16,17],"分散式系統","技術演講","學習路徑","生產經驗","系統設計","zh",0,false,"2026-05-18T03:33:21.6849+00:00","2026-05-18T03:33:21.641+00:00","done","49ee8645-300b-478d-9590-27b5a606dd6e","weishenme-fensanshi-xitong-yanjiang-bi-buluoge-wenzhang-geng-zh","research","bdbdabd8-3175-483a-aa57-a36d9d7abf12","published",[30,31,32],"演講能把理論、故障與修正放在同一脈絡，學習效率通常高於零散文章。","真正有價值的內容來自案例與 postmortem，而不是包裝過的最佳實踐。","先建立失敗與取捨的心智模型，再動手實作，能降低 production 學費。","0c35a120-52fc-41fc-afa3-d404eb934158","[-0.0030304184,-0.008320394,0.011741903,-0.05492701,-0.009447674,-0.00377544,-0.022694184,-0.009571718,-0.007761228,0.027456839,-0.009895045,-0.015356414,0.027845439,0.013055772,0.12756972,0.01670843,0.03469877,0.018238572,0.013321735,0.007659107,0.03786111,0.004788893,0.015124459,-0.026634179,0.014579347,-0.0065505607,0.010437679,0.00023610299,0.020158269,0.0024806724,0.016723553,0.045735672,-0.0009261962,0.03218331,0.0006772646,-0.005066894,0.016324222,-0.012632831,0.0058107367,0.015678843,-0.015443961,0.0027676101,0.0025431886,-0.028182557,-0.012412089,0.009920489,0.00020707354,-0.009278672,0.0066897343,0.0062603215,-0.0036786492,-0.003433585,0.029216038,-0.18058513,-0.013569332,0.0051838355,0.0025788671,0.004412993,-0.01749901,0.00440592,0.0010166158,-0.00063673925,-0.023294386,-0.012233481,0.0019371032,-0.028318161,0.013987668,-0.009110889,-0.0033833706,0.013777296,-0.0020431594,0.0052693593,0.005309261,-0.0054765795,0.013095852,-0.012117038,-0.0051229605,-0.006712255,0.013403882,0.018736793,-0.026386216,-0.021107,0.0038770365,-0.009191879,-0.0058114855,0.0064400756,0.009697428,-0.012182463,0.006671784,0.04548782,0.003692835,-0.015892403,-0.0007180864,0.0077030393,0.007723919,-0.007358094,0.005072475,-0.03109903,0.010002503,-0.0064070155,0.004680943,0.0013441419,0.0055867694,0.0031414002,-0.0021799372,-0.007616393,0.0067487666,0.0005399255,-0.009326155,0.0047436436,-0.017235482,-0.014870113,-0.009660293,-0.0083599,-0.004995422,-0.1337592,-0.0005137926,0.0069453223,-0.012379763,0.0025446184,0.00091265794,-0.0022415307,0.033697244,-0.0038429957,-0.02001959,0.004025142,0.00447927,0.0052037104,0.0009263049,-0.028124964,0.0035356476,-0.009731348,0.0026002638,0.009757595,0.0052740197,0.01806346,0.003929934,-0.033070385,-0.026569776,-0.032085165,-0.0026802295,0.016349863,0.0378611,0.0111757815,-0.030023793,-0.014551914,-0.057044815,0.012939083,-0.008202995,-0.014680781,0.029852979,0.026490798,0.030406564,0.02390037,0.036266994,-0.01467543,0.015703266,-0.004023954,-0.008748314,0.012502711,-0.00060961675,0.011319936,0.018527737,0.005832747,0.010758107,0.019682918,-0.032872256,0.010791896,-0.00082833617,0.009830887,0.0037461668,0.0025866928,-0.037036374,0.0008545499,0.014059862,-0.001958936,-0.016256167,0.028852398,0.02239745,-0.02443677,-0.0029646487,-0.02267887,-0.010284461,0.045452647,-0.02443267,0.0071262764,-0.020502295,0.0063950717,0.0075720246,0.003366991,-0.019083599,-0.019808142,0.015872065,0.008350939,-0.011683079,-0.06373928,0.01305499,0.018576065,0.0007545189,0.010848189,0.00994901,-0.014535554,0.02908485,-0.02927723,0.00037456895,-0.012473333,-0.0026354664,0.00012654289,0.006893633,0.0050189192,-0.013545605,-0.00637987,0.0026426737,-0.037220627,-0.0040382533,-0.012684676,-0.014989959,-0.01911182,-0.0017634559,-0.013325394,0.004273921,-0.010617779,0.012168688,0.001331749,-0.00029745928,-0.023482408,0.0023788344,0.0097563,-0.0025187177,0.024295531,0.0055506746,0.033065476,-0.018938549,0.00056132494,0.01192623,0.047094267,0.03256376,0.021021642,0.002215164,0.022606215,-0.009783913,0.0065852236,-0.0049613104,0.04196557,-0.01111107,-0.0037671672,0.0092941085,0.01699097,0.0064991903,0.017878225,0.023074888,0.0039801374,0.016630959,0.0009236361,0.021547062,-0.019215042,-0.01854975,0.0054798764,0.012187842,0.005175473,-0.025352104,-0.022830015,-0.0013757733,-0.023410432,0.01014286,0.015959065,-0.0030332676,-0.011174888,-0.027497217,-0.016125204,-0.016872399,0.008048269,-0.008045087,-0.010809343,-0.010939336,0.023990426,-0.07418982,-0.010551458,0.008253772,0.008618079,0.01399954,-0.019855246,0.014342084,0.032182023,-0.026275713,-0.003918148,-0.025703942,-0.021458657,-0.0054925443,-0.0033816556,0.019538041,-0.00021563937,-0.008499996,-0.0052662487,-0.012931755,-0.003040248,0.01344556,0.00932449,-0.018006971,0.0042302427,0.0009875984,-0.018138971,-0.041628476,0.03406666,-0.0039831805,0.011894196,0.023409134,0.0023745948,0.015682729,0.04085077,-0.011368114,-0.027322527,0.010038077,-0.0018270749,-0.014805939,0.0057557896,0.0052350247,0.007590853,-0.026765503,-0.016191851,-0.023078242,-0.01043165,-0.008566761,0.022648698,-0.038501628,0.013991689,0.011932764,-0.01308201,0.0009054619,-0.011142481,0.00571915,0.019418389,0.017831778,-0.009426194,-0.025128836,0.0060986998,-0.007636955,0.008596862,-0.034861363,0.032715037,-0.009074453,-0.00076198287,-0.002096717,-0.019523572,-0.021012755,0.00830264,-0.016811758,-0.011973182,-0.00881604,-0.034734283,0.013562114,-0.0011450466,-0.011543876,-0.014467575,-0.023620185,0.010446046,0.018560939,0.024301602,0.016465168,0.007894344,0.017403105,-0.026121829,-0.0113519,0.014215817,0.013128984,-0.028350422,-0.011681026,0.032955207,-0.021593556,-0.013592422,-0.01371101,0.0093456935,0.016440326,0.009659897,-0.00089388026,-0.01076359,0.0012323085,0.01688088,-0.02210169,-0.02053727,0.0073409392,0.024031537,-0.009533538,0.0019442267,-0.015399813,0.0006982013,0.030997511,-0.018493751,-0.012866491,-0.012411365,0.014324793,-0.012371481,0.03176828,0.017061412,-0.014916907,-0.020437358,-0.0021419257,0.0046283277,-0.01860823,-0.010947107,-0.035747826,-0.0030997216,0.00730607,0.0007868301,0.012280861,-0.010628164,0.016448716,-0.0059332517,0.0011422187,-0.015325072,0.0017304405,-0.023280745,0.014339996,0.036323782,0.0043691793,-0.0046825744,-0.0010223705,0.021070674,0.003909178,-0.0065757306,0.011065752,0.010108836,-0.02393088,-0.016676636,0.008058705,-0.008034727,-0.034486245,-0.019226357,-0.017787326,-0.037297502,0.027478345,0.009897416,0.013058211,-0.01687029,-0.002552151,-0.029175371,-0.017182695,-0.013434884,0.0068444572,0.0006026451,-0.023407608,-0.0127372425,-0.012319668,-0.0075578876,0.02622761,-0.029272908,0.006084958,0.0068828105,-0.03765467,0.012045587,0.032756705,0.045528647,-0.014638701,-0.022678321,0.020797323,-0.00046869915,-0.027254706,0.028446434,-0.0004428249,-0.041346803,0.00018091682,-0.03329962,0.010716713,0.0025765111,0.010901867,-0.03663009,-0.020264585,-0.015490784,-0.032106604,0.02160503,0.022419116,0.004244945,-0.025398463,0.006576696,-0.00759145,0.023287421,-0.010195659,0.0011528711,0.0075727236,-0.014815527,0.0274311,-0.009618882,0.011484133,-0.011993234,0.0038753469,0.019939018,-0.016777538,0.03406276,-0.008514794,0.016405813,-0.009692013,0.033449385,-0.0061209197,-0.009032309,-0.019363197,-0.025978973,0.0030977456,-0.016016228,0.0031053424,-0.020107055,-0.004039401,0.019392557,-0.013735882,-0.0011950603,0.0001854557,0.0063375016,0.011465541,0.016996924,-0.0025095183,-0.009865076,-0.0137713505,0.008230374,-0.007531235,-0.008325186,-0.017154368,0.011761063,0.0115690995,0.0043591373,-0.0055396548,0.0062320735,0.019823836,-0.030412659,0.015520919,0.016016923,-0.004705689,-0.033176534,0.031093646,0.009243699,0.016729586,0.032870222,-0.0028310854,0.04023948,-0.004993028,-0.025503822,0.027142681,-0.027086224,-0.017629996,0.008186919,0.009317805,-0.0107056955,-0.014556054,0.016283616,0.0042307503,-0.008666923,0.026939038,-0.11616457,0.017075863,-0.016907891,-0.0047316384,0.004519255,-0.01634561,-0.0007003854,-0.015169905,0.006825602,0.021070827,-0.0053756055,-0.0022340717,0.055319358,-0.012057044,0.013594032,-0.036275763,-0.024880083,0.016607886,0.017251916,0.01469371,0.025947336,0.0011089429,-0.0117342435,0.031522058,-0.024371494,0.00087085634,0.036109187,0.02052353,0.0041985624,-0.0070860265,-0.011531586,-0.0073551694,0.020585706,0.007138685,0.008014157,-0.015037029,0.029407749,-0.03702882,-0.0030353747,0.017418243,0.007097792,-0.006633188,-0.024706872,-0.0007168604,0.01463701,-0.008380547,-0.018120902,-0.01248054,0.0025234027,0.0055972673,-0.004206988,-0.025314547,-0.0006937797,-0.030614354,-0.00490073,0.0027677426,-0.0031558434,-0.0029918605,-0.0008330699,-0.007098498,-0.0014993116,0.028304214,-0.026049916,-0.00037119852,-0.012539581,-0.028585082,0.0039642733,0.0072855013,0.016143002,0.015929561,-0.021404801,0.032206647,-0.012095664,-0.011671732,-0.0210243,0.0060234205,-0.017583236,0.015280134,0.006251081,0.009217389,-0.016384194,0.01160105,-0.06664829,0.0009804819,-0.014405934,-0.018961783,0.007135307,0.0061215754,-0.00065490435,0.0067718416,-0.0032634102,-0.0023846268,-0.018811088,-0.026208524,-0.01763307,0.009500799,0.011849397,-0.006827063,0.010439112,-0.014347196,0.020397376,-0.013607303,0.022564717,-0.0017845768,-0.00590712,-0.024469566,-0.0269609,0.0016273159,0.012451817,0.0016714942,-0.0020416528,-0.0068100984,-0.014450677,-0.10991341,-0.023881005,0.021618174,-0.005335556,0.026666095,0.027780628,-0.021311268,-0.025984481,0.0036471698,-0.015574199,-0.031786967,0.0135751115,-0.018546823,-0.01887502,-0.012011282,0.12002682,0.0039168634,-0.0073254625,-0.007255827,-0.035590436,-0.005842336,-0.02967078,-0.007774255,-0.0031205765,-0.009942942,0.010115132,0.013894984,-0.023950405,-0.004345079,0.011446673,-0.0022982436,-0.008125349,-0.033071224,-0.016398994,-0.0023515974,-0.029602502,-0.012028721,-0.016488625,0.010236419,-0.005175032,-0.011980412,-0.005802777,0.008746556,0.0025976477,0.0024548105,-0.00231212,-0.013421155,-0.012601741,-0.0030077319,-0.0011526532,-0.02335035,-0.052880526,0.0067016855,-0.02596195,0.003177734,0.00022871791,-0.0012562862,0.026549518,-0.0019785971,0.007133736,0.0049248897,0.006391886,0.025009962,0.024937121,-0.0053577507,-0.011029904,0.014830277,0.025575897,0.014467285,0.029137231,0.007192174,-0.00079031766,-0.0062943227,-0.012867158,0.031735323,-0.0009813557,-0.00024825174,0.0110643525,0.005052437,-0.011052272,0.021043133,0.012723199,-0.024646739,-0.01179245,0.015599379,-0.028830385,0.03885001,0.041768435,0.0019566263,-0.02673166,0.019669667,0.042608295,0.00034764202,0.03270252,-2.7773522e-05,0.0100637525,0.01659492,0.019394353,-0.007028374,-0.016543519,0.0078643495,-0.010959313,0.0075877644,-0.010411751,0.006508961,-0.007170534,0.0057358295,-0.015856292,0.035169873,-0.015824528]",{"tags":36,"relatedLang":42,"relatedPosts":46},[37,38,39,40,41],{"name":15,"slug":15},{"name":17,"slug":17},{"name":13,"slug":13},{"name":14,"slug":14},{"name":16,"slug":16},{"id":27,"slug":43,"title":44,"language":45},"why-distributed-systems-talks-beat-blog-posts-en","Why Distributed Systems Talks Beat Blog Posts for Real Learning","en",[47,53,59,65,71,77],{"id":48,"slug":49,"title":50,"cover_image":51,"image_url":51,"created_at":52,"category":26},"7c89c3bd-48cb-4b4e-942d-bbf0409fc392","cattle-trade-llm-bluffing-bargaining-benchmark-zh","Cattle Trade 要測 LLM 談判 bluffing","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779085437419-b0zw.png","2026-05-18T06:23:27.885037+00:00",{"id":54,"slug":55,"title":56,"cover_image":57,"image_url":57,"created_at":58,"category":26},"492aa1ec-02ce-491e-ad03-ae804f261f87","weak-rewards-persistent-llm-user-models-zh","弱回饋讓 LLM 記住偏好","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779084838002-5od2.png","2026-05-18T06:13:32.906335+00:00",{"id":60,"slug":61,"title":62,"cover_image":63,"image_url":63,"created_at":64,"category":26},"9580adce-69ec-4880-ad8b-227c384cb377","marlin-greener-llm-inference-datacenters-zh","MARLIN 用多代理 RL 省雲端推理資源","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779084247021-qzhd.png","2026-05-18T06:03:35.259834+00:00",{"id":66,"slug":67,"title":68,"cover_image":69,"image_url":69,"created_at":70,"category":26},"0b28782b-fc24-49fc-bc5c-ec9c07c8ad46","wei-shen-me-sora-zheng-ming-ying-pian-ai-hai-mei-zhun-bei-ha-zh","為什麼 Sora 證明影片 AI 還沒準備好走向主流","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779059031003-tsg7.png","2026-05-17T23:03:22.155232+00:00",{"id":72,"slug":73,"title":74,"cover_image":75,"image_url":75,"created_at":76,"category":26},"aefdd28e-fccb-46ca-a78b-ad6ad718058d","microsoft-mdash-finds-16-windows-flaws-zh","Microsoft MDASH 找出 16 個 Windows 漏洞","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779041037625-66oq.png","2026-05-17T18:03:35.214691+00:00",{"id":78,"slug":79,"title":80,"cover_image":81,"image_url":81,"created_at":82,"category":26},"902b314d-316c-48aa-9a2a-e4d16f32d2ac","browser-exploit-benchmarks-prove-ai-security-here-zh","為什麼瀏覽器 exploit 基準已證明 AI 安全威脅就在眼前","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779019382261-mfmw.png","2026-05-17T08:03:21.360298+00:00",[84,89,94,99,104,109,114,119,124,129],{"id":85,"slug":86,"title":87,"created_at":88},"f18dbadb-8c59-4723-84a4-6ad22746c77a","deepmind-bets-on-continuous-learning-ai-2026-zh","DeepMind 押注 2026 連續學習 AI","2026-03-26T08:16:02.367355+00:00",{"id":90,"slug":91,"title":92,"created_at":93},"f4a106cb-02a6-4508-8f39-9720a0a93cee","ml-papers-of-the-week-github-research-desk-zh","每週 ML 論文清單，為何紅到 GitHub","2026-03-27T01:11:39.284175+00:00",{"id":95,"slug":96,"title":97,"created_at":98},"c4f807ca-4e5f-47f1-a48c-961cf3fc44dc","ai-ml-conferences-to-watch-in-2026-zh","2026 AI 研討會投稿時程整理","2026-03-27T01:51:53.874432+00:00",{"id":100,"slug":101,"title":102,"created_at":103},"9f50561b-aebd-46ba-94a8-363198aa7091","openclaw-agents-manipulated-self-sabotage-zh","OpenClaw Agent 會自己搞砸自己","2026-03-28T03:03:18.786425+00:00",{"id":105,"slug":106,"title":107,"created_at":108},"11f22e92-7066-4978-a544-31f5f2156ec6","vega-learning-to-drive-with-natural-language-instructions-zh","Vega：使用自然語言指示進行自駕車控制","2026-03-28T14:54:04.847912+00:00",{"id":110,"slug":111,"title":112,"created_at":113},"a4c7cfec-8d0e-4fec-93cf-1b9699a530b8","drive-my-way-en-zh","Drive My Way：個性化自駕車風格的實現","2026-03-28T14:54:26.207495+00:00",{"id":115,"slug":116,"title":117,"created_at":118},"dec02f89-fd39-41ba-8e4d-11ede93a536d","training-knowledge-bases-with-writeback-rag-zh","用 WriteBack-RAG 強化知識庫提升檢索效能","2026-03-28T14:54:45.775606+00:00",{"id":120,"slug":121,"title":122,"created_at":123},"3886be5c-a137-40cc-b9e2-0bf18430c002","packforcing-efficient-long-video-generation-method-zh","PackForcing：短影片訓練也能生成長影片","2026-03-28T14:55:02.688141+00:00",{"id":125,"slug":126,"title":127,"created_at":128},"72b90667-d930-4cc9-8ced-aaa0f8968d44","pixelsmile-toward-fine-grained-facial-expression-editing-zh","PixelSmile：提升精細臉部表情編輯的新方法","2026-03-28T14:55:20.678181+00:00",{"id":130,"slug":131,"title":132,"created_at":133},"cf046742-efb2-4753-aef9-caed5da5e32e","adaptive-block-scaled-data-types-zh","IF4：神經網路量化的聰明選擇","2026-03-31T06:00:36.990273+00:00"]