[{"data":1,"prerenderedAt":347},["ShallowReactive",2],{"tag-labels":3,"site-header":4,"article-kenapa-ai-suka-halu-kenalan-sama-jepa-otak-ai-yang-punya-akal-sehat-id":72},{},{"featuredPost":5,"navigations":29},{"id":6,"title":7,"title_en":8,"slug":9,"excerpt":10,"excerpt_en":11,"has_translation":12,"published_at":13,"reading_time":14,"hidden_from_listing":15,"tags":16,"thumbnail_image":21,"og_image":22,"series":23,"authors":28},110,"Ketika Pilih Framework Cuma Biar Kelihatan Beda","When You Pick a Framework Just to Look Different","ketika-pilih-framework-cuma-biar-kelihatan-beda","Terakhir kali kamu milih framework atau library baru, itu karena masalahmu butuh alat itu, atau karena alatnya kedengaran keren dan belum banyak yang pakai? Pertanyaan ini nggak enak dijawab. Soalnya keputusan teknologi sering diambil dengan alasan yang nggak pernah ditulis di dokumen teknis mana pun.","The last time you chose a new framework or library, was it because your problem needed that tool, or because it sounded cool and few people around you were using it? That question is uncomfortable. Technology decisions are often made for reasons that never appear in any technical document.",true,"2026-10-06T15:25:21.000Z",5,false,[17,18,19,20],"karier","framework","opini","pengalaman",null,"\u002Fog\u002Fketika-pilih-framework-cuma-biar-kelihatan-beda.png",{"id":24,"title":25,"title_en":26,"slug":27},9,"Artikel","Articles","all",[],[30,46,67],{"collection":31,"item":32},"series",{"__typename":31,"title":25,"title_en":26,"slug":27,"children_series":33},[34,38,42],{"title":35,"title_en":36,"slug":37},"Kecerdasan Artifisial","Artificial Intelligence","kecerdasan-artifisial",{"title":39,"title_en":40,"slug":41},"Konsep Dasar Pemrograman","Programming Fundamentals","konsep-dasar-pemrograman",{"title":43,"title_en":44,"slug":45},"Algoritma dan Struktur Data","Algorithms and Data Structures","algoritma-struktur-data",{"collection":31,"item":47},{"__typename":31,"title":48,"title_en":48,"slug":49,"children_series":50},"Tutorial","tutorial",[51,55,59,63],{"title":52,"title_en":53,"slug":54},"Belajar Python","Learning Python","belajar-python",{"title":56,"title_en":57,"slug":58},"Belajar Golang","Learning Go","belajar-golang",{"title":60,"title_en":61,"slug":62},"Belajar Java","Learning Java","belajar-java",{"title":64,"title_en":65,"slug":66},"Belajar Pascal","Learning Pascal","belajar-pascal",{"collection":31,"item":68},{"__typename":31,"title":69,"title_en":69,"slug":70,"children_series":71},"Lab","lab",[],{"article":73,"renderedBody":262,"renderedTakeaway":263,"latestArticles":264,"toc":331},{"id":74,"title":75,"title_en":76,"slug":77,"excerpt":78,"excerpt_en":79,"has_translation":12,"published_at":80,"reading_time":81,"hidden_from_listing":15,"tags":82,"thumbnail_image":21,"og_image":87,"series":88,"authors":257,"body_locale":258,"available_locales":259,"body":261,"takeway":21,"prerequisite":21},1,"Kenapa AI Suka 'Halu'? Kenalan sama JEPA, Otak AI yang Punya Akal Sehat","Why Does AI Keep Hallucinating? Meet JEPA, the AI Brain With Common Sense","kenapa-ai-suka-halu-kenalan-sama-jepa-otak-ai-yang-punya-akal-sehat","AI generatif sering 'halu' karena cuma jago nebak pola kata. JEPA coba ngerombak itu dengan ngajarin AI cara kerja dunia nyata kayak otak manusia.","Generative AI hallucinates because all it does is guess word patterns. JEPA tries to change that by teaching machines how the real world works, the way a human brain does.","2026-06-02T08:09:05.595Z",4,[83,84,85,86],"jepa","artificial-intelligence","yann-lecun","agi","\u002Fog\u002Fkenapa-ai-suka-halu-kenalan-sama-jepa-otak-ai-yang-punya-akal-sehat.png",{"id":89,"title":35,"title_en":36,"slug":37,"description":21,"description_en":90,"articles":91,"children_series":249,"parent_series":250},8,"Notes on AI that go past the demo: how the models work, where they break, and what changes once you put them in production.",[92,95,113,128,142,156,173,190,211,230],{"id":74,"title":75,"title_en":76,"slug":77,"excerpt":78,"excerpt_en":79,"has_translation":12,"published_at":80,"reading_time":81,"hidden_from_listing":15,"tags":82,"thumbnail_image":21,"og_image":87,"series":93,"authors":94},{"id":89,"title":35,"title_en":36,"slug":37},[],{"id":96,"title":97,"title_en":98,"slug":99,"excerpt":100,"excerpt_en":101,"has_translation":12,"published_at":102,"reading_time":81,"hidden_from_listing":15,"tags":103,"thumbnail_image":21,"og_image":105,"series":106,"authors":107},2,"LLM Bakal Mentok, Terus Gimana Dong?","LLMs Are Going to Hit a Wall. What Then?","llm-bakal-mentok-terus-gimana-dong","LLM kayak ChatGPT itu jago ngerangkai kata, tapi nggak beneran paham realitas. Yann LeCun bilang arsitektur ini bakal mentok dan butuh solusi baru.","LLMs like ChatGPT are great at stringing words together, but they never really grasp reality. Yann LeCun says this architecture will hit a wall and needs a new answer.","2026-06-03T08:55:33.003Z",[84,104,85,83],"llm","\u002Fog\u002Fllm-bakal-mentok-terus-gimana-dong.png",{"id":89,"title":35,"title_en":36,"slug":37},[108],{"authors_id":109},{"id":74,"name":110,"slug":111,"role":112,"profile_picture":21},"Daffa Izzuddin","izzudd","Writer",{"id":114,"title":115,"title_en":116,"slug":117,"excerpt":118,"excerpt_en":119,"has_translation":12,"published_at":120,"reading_time":81,"hidden_from_listing":15,"tags":121,"thumbnail_image":21,"og_image":123,"series":124,"authors":125},3,"Mengenal JEPA: Saat AI Mulai Belajar Punya \"Akal Sehat\"","Meet JEPA: Where AI Starts Learning Common Sense","kenapa-ai-suka-halu-dan-gimana-jepa-beresin-masalah-ini","AI sering 'halu' karena cuma nebak probabilitas data tanpa paham realita. Arsitektur JEPA mencoba mengubah itu dengan membangun model dunia di kepalanya.","AI hallucinates because it only guesses data probabilities without understanding reality. The JEPA architecture tries to change that by building a world model in its head.","2026-06-03T09:32:50.446Z",[84,83,122,85],"world-models","\u002Fog\u002Fkenapa-ai-suka-halu-dan-gimana-jepa-beresin-masalah-ini.png",{"id":89,"title":35,"title_en":36,"slug":37},[126],{"authors_id":127},{"id":74,"name":110,"slug":111,"role":112,"profile_picture":21},{"id":81,"title":129,"title_en":130,"slug":131,"excerpt":132,"excerpt_en":133,"has_translation":12,"published_at":134,"reading_time":81,"hidden_from_listing":15,"tags":135,"thumbnail_image":21,"og_image":137,"series":138,"authors":139},"Bukan Sekadar Generative AI, JEPA Coba Kejar Pemahaman Konsep ala Manusia","Beyond Generative AI: JEPA Chases Human-Style Conceptual Understanding","kenapa-ai-masih-gagal-paham-fisika-dasar-mengenal-arsitektur-jepa","AI biasanya cuma jago nebak piksel, tapi JEPA coba belajar lewat konsep abstrak di ruang laten. Ternyata, cara ini bisa sampai dipakai buat baca gelombang otak.","AI usually only guesses pixels, while JEPA tries to learn from abstract concepts in latent space. That approach turns out to reach as far as reading brain waves.","2026-06-03T09:34:14.840Z",[83,85,136,86],"machine-learning","\u002Fog\u002Fkenapa-ai-masih-gagal-paham-fisika-dasar-mengenal-arsitektur-jepa.png",{"id":89,"title":35,"title_en":36,"slug":37},[140],{"authors_id":141},{"id":74,"name":110,"slug":111,"role":112,"profile_picture":21},{"id":14,"title":143,"title_en":144,"slug":145,"excerpt":146,"excerpt_en":147,"has_translation":12,"published_at":148,"reading_time":81,"hidden_from_listing":15,"tags":149,"thumbnail_image":21,"og_image":151,"series":152,"authors":153},"Di Balik Dapur JEPA: Rahasia EMA, VICReg, dan Efisiensi Komputasi","Inside JEPA's Kitchen: The Secrets of EMA, VICReg, and Compute Efficiency","di-balik-dapur-jepa-rahasia-ema-vicreg-dan-efisiensi-komputasi","Bosen sama AI yang cuma jago nebak kata atau ngafalin pixel? Kenalan sama JEPA, arsitektur revolusioner yang ngajarin mesin punya \"akal sehat\" secara super efisien. Yuk intip jeroan teknisnya!","Bored of AI that only guesses words or memorizes pixels? Meet JEPA, an architecture that teaches machines common sense very cheaply. Here is a look at its technical insides.","2026-06-07T16:14:13.723Z",[83,150],"artificial-intelligent","\u002Fog\u002Fdi-balik-dapur-jepa-rahasia-ema-vicreg-dan-efisiensi-komputasi.png",{"id":89,"title":35,"title_en":36,"slug":37},[154],{"authors_id":155},{"id":74,"name":110,"slug":111,"role":112,"profile_picture":21},{"id":157,"title":158,"title_en":159,"slug":160,"excerpt":161,"excerpt_en":162,"has_translation":12,"published_at":163,"reading_time":89,"hidden_from_listing":15,"tags":164,"thumbnail_image":21,"og_image":170,"series":171,"authors":172},125,"MCP dibongkar ulang: kabar baik buat kamu yang capek nulis konektor","MCP, Rebuilt: Good News If You're Tired of Writing Connectors","mcp-dibongkar-ulang-kabar-baik-buat-kamu","Kamu punya beberapa API internal dan satu agent AI, tapi kodenya harus ditulis ulang tiap kali modelnya diganti. MCP datang buat mengakhiri itu, dan tahun ini protokolnya dibongkar ulang supaya server-nya bisa jalan seperti web server biasa. Yuk lihat apa yang berubah. 🔧","You have a few internal APIs and one AI agent, but the code has to be rewritten every time the model changes. MCP ends that, and this year the protocol was rebuilt so servers can run like ordinary web servers. Here's what changed. 🔧","2026-10-16T05:00:00.000Z",[165,166,167,104,168,169],"mcp","model-context-protocol","ai-agent","backend","python","\u002Fog\u002Fmcp-dibongkar-ulang-kabar-baik-buat-kamu.png",{"id":89,"title":35,"title_en":36,"slug":37},[],{"id":174,"title":175,"title_en":176,"slug":177,"excerpt":178,"excerpt_en":179,"has_translation":12,"published_at":180,"reading_time":181,"hidden_from_listing":15,"tags":182,"thumbnail_image":21,"og_image":185,"series":186,"authors":187},126,"Memori AI Agent: dari Vector Store ke Temporal Graph","AI Agent Memory: From Vector Store to Temporal Graph","memori-ai-agent-vector-store-ke-temporal-graph","Dua fakta yang saling bertentangan bikin agent menjawab ngawur. Ini bedanya vector store dan temporal knowledge graph dalam menjaga state jangka panjang.","Two contradictory facts make an agent answer nonsense. Here is how a vector store and a temporal knowledge graph differ at keeping long-term state.","2026-10-18T13:13:29.458Z",7,[183,104,168,184],"ai","system-design","\u002Fog\u002Fmemori-ai-agent-vector-store-ke-temporal-graph.png",{"id":89,"title":35,"title_en":36,"slug":37},[188],{"authors_id":189},{"id":74,"name":110,"slug":111,"role":112,"profile_picture":21},{"id":191,"title":192,"title_en":193,"slug":194,"excerpt":195,"excerpt_en":196,"has_translation":12,"published_at":197,"reading_time":198,"hidden_from_listing":15,"tags":199,"thumbnail_image":21,"og_image":206,"series":207,"authors":208},127,"Kenapa RAG yang cuma andalkan cosine similarity sering nyasar","Why RAG That Leans on Cosine Similarity Alone Keeps Missing","kenapa-rag-cuma-cosine-similarity-sering-nyasar","RAG yang cuma andalkan embedding balikin chunk yang mirip maknanya, bukan yang kamu butuh. Ini penyebabnya, dan dua lapis penambalnya.","RAG that leans only on embeddings returns chunks that look close in meaning, not the ones you need. Here is why, and the two layers that patch it.","2026-10-19T02:04:06.718Z",6,[200,201,202,203,204,205],"rag","vector-search","bm25","hybrid-search","retrieval","embedding","\u002Fog\u002Fkenapa-rag-cuma-cosine-similarity-sering-nyasar.png",{"id":89,"title":35,"title_en":36,"slug":37},[209],{"authors_id":210},{"id":74,"name":110,"slug":111,"role":112,"profile_picture":21},{"id":212,"title":213,"title_en":214,"slug":215,"excerpt":216,"excerpt_en":217,"has_translation":12,"published_at":218,"reading_time":198,"hidden_from_listing":15,"tags":219,"thumbnail_image":21,"og_image":225,"series":226,"authors":227},128,"Linear atau graf: cara mengatur banyak agent tanpa loop abadi","Linear or Graph: How to Run Many Agents Without an Eternal Loop","multi-agen-linear-atau-grafik","Satu agent dengan dua puluh tool gampang kacau. Begitu beberapa agent saling revisi, kamu butuh graf yang mendukung cycle dan angka yang membuatnya berhenti.","One agent with twenty tools gets messy fast. Once several agents revise each other, you need a graph that allows cycles and a number that makes it stop.","2026-10-21T16:05:00.000Z",[220,221,222,223,224,104],"multi-agent","langgraph","autogen","orkestrasi","checkpoint","\u002Fog\u002Fmulti-agen-linear-atau-grafik.png",{"id":89,"title":35,"title_en":36,"slug":37},[228],{"authors_id":229},{"id":74,"name":110,"slug":111,"role":112,"profile_picture":21},{"id":231,"title":232,"title_en":233,"slug":234,"excerpt":235,"excerpt_en":236,"has_translation":12,"published_at":237,"reading_time":14,"hidden_from_listing":15,"tags":238,"thumbnail_image":21,"og_image":244,"series":245,"authors":246},129,"Biar RAG nggak kena 504: pisahin jalur query dan ingestion","So Your RAG Stops Hitting 504: Split the Query Path From Ingestion","rag-pisah-jalur-query-dan-ingestion","Satu service RAG yang merangkap parsing dan menjawab kueri bakal tumbang pas ada yang upload PDF 200 halaman. Obatnya dua jalur dan satu queue.","One RAG service that both parses uploads and answers queries will fall over the moment someone uploads a 200-page PDF. The cure is two paths and one queue.","2026-10-22T01:30:00.000Z",[200,239,240,241,242,243],"cloud-run","cloud-tasks","gcp","serverless","arsitektur","\u002Fog\u002Frag-pisah-jalur-query-dan-ingestion.png",{"id":89,"title":35,"title_en":36,"slug":37},[247],{"authors_id":248},{"id":74,"name":110,"slug":111,"role":112,"profile_picture":21},[],{"id":24,"title":25,"title_en":26,"slug":27,"parent_series":21,"children_series":251},[252,253,255],{"id":89,"title":35,"title_en":36,"slug":37,"cover_image":21},{"id":254,"title":39,"title_en":40,"slug":41,"cover_image":21},12,{"id":256,"title":43,"title_en":44,"slug":45,"cover_image":21},15,[],"id",[260,258],"en","\nNgomongin soal AI akhir-akhir ini, pasti yang langsung kepikiran di kepala kita itu ChatGPT, Claude, atau AI pembuat gambar generatif kan? Harus diakui, mereka memang pintar banget. Tapi, pernah nggak sih kamu ngerasa kalau AI ini kadang suka \"halu\" atau ngasih jawaban yang secara logika fisik itu nggak masuk akal?\n\nWajar aja, soalnya AI generatif yang populer sekarang itu ibarat \"burung beo\" tingkat dewa. Mereka jago merangkai kata atau menebak pixel gambar, tapi *nggak benar-benar paham* gimana dunia nyata bekerja.\n\nNah, di sinilah **JEPA** masuk. Konon, ini adalah kunci supaya AI di masa depan nggak cuma jago ngomong, tapi juga punya *common sense* alias akal sehat. Yuk, kita bedah pelan-pelan!\n\n---\n\n## Jadi, Apa Sebenarnya JEPA Itu?\n\nJEPA adalah singkatan dari ***Joint Embedding Predictive Architecture***. Istilahnya memang agak teknis, tapi gampangnya: ini adalah jenis \"otak\" AI model baru yang digagas oleh Yann LeCun, bos ilmuwan AI di Meta (induk perusahaannya Facebook, Instagram, dkk).\n\nKalau AI generatif diajari untuk fokus meniru pola dari triliunan teks di internet, JEPA didesain dengan pondasi yang beda banget. JEPA dirancang buat **memahami cara kerja dunia nyata**, persis kayak gimana manusia dan hewan mengamati sekitarnya.\n\n## Gimana Sih Cara Kerjanya? (Spoiler: Anti Perfeksionis!)\n\nKelemahan AI generatif biasa adalah mereka itu terlalu \"perfeksionis\". Kalau disuruh menebak kelanjutan sebuah video, AI biasa akan ngotot mencoba menebak detail **setiap titik pixel**. Mereka mau nebak arah angin meniup tiap helai rambut, atau pantulan cahaya di kaca. Hasilnya? Komputernya jadi berat, boros energi, dan ujung-ujungnya malah sering salah alias *glitch*.\n\nCara kerja JEPA justru sebaliknya: **dia nggak peduli sama detail kecil yang nggak penting.** Dia cuma fokus menebak \"konsep abstrak\" atau gambaran besarnya aja.\n\n**Coba bayangin gini:** Kamu lagi duduk di kafe, terus ngeliat ada orang nyenggol gelas kaca di ujung meja. Sebagai manusia, kamu pasti otomatis mikir, *\"Wah, gelasnya bakal jatuh dan pecah nih.\"* Apakah otakmu repot-repot menghitung sudut jatuhnya gelas, letak ratusan serpihan kacanya nanti ke arah mana, atau suara pecahnya sekencang apa? Nggak, kan? Kamu cuma paham konsep dasarnya. Nah, JEPA bekerja persis seperti otak manusia di situasi ini!\n\n## Terus, Kegunaannya Buat Apa Dong?\n\nKarena JEPA ini paham \"hukum alam\", kegunaannya bakal sangat praktis buat teknologi yang langsung berinteraksi dengan dunia fisik. Beberapa contohnya:\n\n- **Robotika yang Makin Pintar:** Saat ini, ngajarin robot buat jalan atau ngeberesin barang itu susahnya minta ampun karena setiap milimeter gerakannya harus diprogram. Dengan otak JEPA, robot bisa langsung paham kalau benda dilepas pasti jatuh, atau kalau dorong meja berat butuh tenaga ekstra. Mereka bisa beradaptasi di lingkungan baru tanpa harus diajari dari nol.\n- **Penglihatan Komputer (Computer Vision):** AI bisa nonton CCTV atau video dan langsung nangkap konteks kejadiannya. Misalnya, sistem bisa langsung bedain mana orang yang lagi main-main, dan mana orang yang lagi berantem beneran.\n- **Kacamata AR\u002FSmart Glasses:** Bayangin kacamata pintar di masa depan yang asisten AI-nya bisa ngeliat jalanan bareng kamu, lalu tiba-tiba ngasih peringatan sedetik sebelum ada mobil nyelonong, karena AI-nya udah memprediksi arah gerak mobil tersebut berdasarkan logika spasial.\n\n## Masa Depan JEPA: Jalan Pintas Menuju AI Super Pintar?\n\nBanyak banget ahli yang setuju kalau masa depan JEPA ini sangat cerah. AI yang murni cuma dilatih pakai teks (seperti LLM yang ada sekarang) lambat laun akan mentok, karena seberapa banyak pun buku yang dibaca AI, mereka nggak akan pernah ngerasain basahnya air atau sakitnya kejedot meja.\n\nJEPA dianggap sebagai jalan pintas menuju **AGI (*****Artificial General Intelligence*****)**, alias AI yang kecerdasannya setara atau bahkan melampaui manusia. Ke depannya, AI yang pakai sistem JEPA:\n\n- **Anti-Halu:** Karena responsnya didasarkan pada logika realitas fisik, bukan sekadar tebak-tebakan statistik kata.\n- **Bisa Bikin Rencana Panjang:** Mampu ngambil keputusan logis yang bertahap, layaknya manusia main catur atau ngerencanain liburan.\n- **Belajar Super Cepat:** Mereka bisa belajar hal baru cuma dari mengamati, secepat balita manusia yang lagi belajar jalan.\n\n---\n\n## Dari Sekadar \"Ngomong\" Jadi \"Mikir\"\n\nKalau kita ibaratkan perkembangan manusia, ChatGPT dan teman-temannya sekarang adalah anak kecil yang jago banget pidato dan hafal kamus. Hebat, tapi belum tentu paham dunia.\n\nDi sisi lain, JEPA adalah pondasi yang lagi dibangun supaya AI masa depan nggak cuma jago ngerangkai kata, tapi juga beneran **jago berpikir dan paham realitas**. Menarik banget kan nungguin gimana teknologi ini bakal ngubah hidup kita beberapa tahun ke depan?\n\nGimana menurutmu, ngeri atau malah *excited* nungguin AI yang makin mirip manusia ini?\n","\u003Cp>Ngomongin soal AI akhir-akhir ini, pasti yang langsung kepikiran di kepala kita itu ChatGPT, Claude, atau AI pembuat gambar generatif kan? Harus diakui, mereka memang pintar banget. Tapi, pernah nggak sih kamu ngerasa kalau AI ini kadang suka "halu" atau ngasih jawaban yang secara logika fisik itu nggak masuk akal?\u003C\u002Fp>\n\u003Cp>Wajar aja, soalnya AI generatif yang populer sekarang itu ibarat "burung beo" tingkat dewa. Mereka jago merangkai kata atau menebak pixel gambar, tapi \u003Cem>nggak benar-benar paham\u003C\u002Fem> gimana dunia nyata bekerja.\u003C\u002Fp>\n\u003Cp>Nah, di sinilah \u003Cstrong>JEPA\u003C\u002Fstrong> masuk. Konon, ini adalah kunci supaya AI di masa depan nggak cuma jago ngomong, tapi juga punya \u003Cem>common sense\u003C\u002Fem> alias akal sehat. Yuk, kita bedah pelan-pelan!\u003C\u002Fp>\n\u003Chr>\n\u003Ch2 id=\"jadi-apa-sebenarnya-jepa-itu\">Jadi, Apa Sebenarnya JEPA Itu?\u003C\u002Fh2>\n\u003Cp>JEPA adalah singkatan dari \u003Cem>\u003Cstrong>Joint Embedding Predictive Architecture\u003C\u002Fstrong>\u003C\u002Fem>. Istilahnya memang agak teknis, tapi gampangnya: ini adalah jenis "otak" AI model baru yang digagas oleh Yann LeCun, bos ilmuwan AI di Meta (induk perusahaannya Facebook, Instagram, dkk).\u003C\u002Fp>\n\u003Cp>Kalau AI generatif diajari untuk fokus meniru pola dari triliunan teks di internet, JEPA didesain dengan pondasi yang beda banget. JEPA dirancang buat \u003Cstrong>memahami cara kerja dunia nyata\u003C\u002Fstrong>, persis kayak gimana manusia dan hewan mengamati sekitarnya.\u003C\u002Fp>\n\u003Ch2 id=\"gimana-sih-cara-kerjanya-spoiler-anti-perfeksionis\">Gimana Sih Cara Kerjanya? (Spoiler: Anti Perfeksionis!)\u003C\u002Fh2>\n\u003Cp>Kelemahan AI generatif biasa adalah mereka itu terlalu "perfeksionis". Kalau disuruh menebak kelanjutan sebuah video, AI biasa akan ngotot mencoba menebak detail \u003Cstrong>setiap titik pixel\u003C\u002Fstrong>. Mereka mau nebak arah angin meniup tiap helai rambut, atau pantulan cahaya di kaca. Hasilnya? Komputernya jadi berat, boros energi, dan ujung-ujungnya malah sering salah alias \u003Cem>glitch\u003C\u002Fem>.\u003C\u002Fp>\n\u003Cp>Cara kerja JEPA justru sebaliknya: \u003Cstrong>dia nggak peduli sama detail kecil yang nggak penting.\u003C\u002Fstrong> Dia cuma fokus menebak "konsep abstrak" atau gambaran besarnya aja.\u003C\u002Fp>\n\u003Cp>\u003Cstrong>Coba bayangin gini:\u003C\u002Fstrong> Kamu lagi duduk di kafe, terus ngeliat ada orang nyenggol gelas kaca di ujung meja. Sebagai manusia, kamu pasti otomatis mikir, \u003Cem>"Wah, gelasnya bakal jatuh dan pecah nih."\u003C\u002Fem> Apakah otakmu repot-repot menghitung sudut jatuhnya gelas, letak ratusan serpihan kacanya nanti ke arah mana, atau suara pecahnya sekencang apa? Nggak, kan? Kamu cuma paham konsep dasarnya. Nah, JEPA bekerja persis seperti otak manusia di situasi ini!\u003C\u002Fp>\n\u003Ch2 id=\"terus-kegunaannya-buat-apa-dong\">Terus, Kegunaannya Buat Apa Dong?\u003C\u002Fh2>\n\u003Cp>Karena JEPA ini paham "hukum alam", kegunaannya bakal sangat praktis buat teknologi yang langsung berinteraksi dengan dunia fisik. Beberapa contohnya:\u003C\u002Fp>\n\u003Cul>\n\u003Cli>\u003Cstrong>Robotika yang Makin Pintar:\u003C\u002Fstrong> Saat ini, ngajarin robot buat jalan atau ngeberesin barang itu susahnya minta ampun karena setiap milimeter gerakannya harus diprogram. Dengan otak JEPA, robot bisa langsung paham kalau benda dilepas pasti jatuh, atau kalau dorong meja berat butuh tenaga ekstra. Mereka bisa beradaptasi di lingkungan baru tanpa harus diajari dari nol.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Penglihatan Komputer (Computer Vision):\u003C\u002Fstrong> AI bisa nonton CCTV atau video dan langsung nangkap konteks kejadiannya. Misalnya, sistem bisa langsung bedain mana orang yang lagi main-main, dan mana orang yang lagi berantem beneran.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Kacamata AR\u002FSmart Glasses:\u003C\u002Fstrong> Bayangin kacamata pintar di masa depan yang asisten AI-nya bisa ngeliat jalanan bareng kamu, lalu tiba-tiba ngasih peringatan sedetik sebelum ada mobil nyelonong, karena AI-nya udah memprediksi arah gerak mobil tersebut berdasarkan logika spasial.\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch2 id=\"masa-depan-jepa-jalan-pintas-menuju-ai-super-pintar\">Masa Depan JEPA: Jalan Pintas Menuju AI Super Pintar?\u003C\u002Fh2>\n\u003Cp>Banyak banget ahli yang setuju kalau masa depan JEPA ini sangat cerah. AI yang murni cuma dilatih pakai teks (seperti LLM yang ada sekarang) lambat laun akan mentok, karena seberapa banyak pun buku yang dibaca AI, mereka nggak akan pernah ngerasain basahnya air atau sakitnya kejedot meja.\u003C\u002Fp>\n\u003Cp>JEPA dianggap sebagai jalan pintas menuju \u003Cstrong>AGI (\u003Cem>\u003Cstrong>\u003Cstrong>Artificial General Intelligence\u003C\u002Fstrong>\u003C\u002Fstrong>\u003C\u002Fem>)\u003C\u002Fstrong>, alias AI yang kecerdasannya setara atau bahkan melampaui manusia. Ke depannya, AI yang pakai sistem JEPA:\u003C\u002Fp>\n\u003Cul>\n\u003Cli>\u003Cstrong>Anti-Halu:\u003C\u002Fstrong> Karena responsnya didasarkan pada logika realitas fisik, bukan sekadar tebak-tebakan statistik kata.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Bisa Bikin Rencana Panjang:\u003C\u002Fstrong> Mampu ngambil keputusan logis yang bertahap, layaknya manusia main catur atau ngerencanain liburan.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Belajar Super Cepat:\u003C\u002Fstrong> Mereka bisa belajar hal baru cuma dari mengamati, secepat balita manusia yang lagi belajar jalan.\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Chr>\n\u003Ch2 id=\"dari-sekadar-ngomong-jadi-mikir\">Dari Sekadar "Ngomong" Jadi "Mikir"\u003C\u002Fh2>\n\u003Cp>Kalau kita ibaratkan perkembangan manusia, ChatGPT dan teman-temannya sekarang adalah anak kecil yang jago banget pidato dan hafal kamus. Hebat, tapi belum tentu paham dunia.\u003C\u002Fp>\n\u003Cp>Di sisi lain, JEPA adalah pondasi yang lagi dibangun supaya AI masa depan nggak cuma jago ngerangkai kata, tapi juga beneran \u003Cstrong>jago berpikir dan paham realitas\u003C\u002Fstrong>. Menarik banget kan nungguin gimana teknologi ini bakal ngubah hidup kita beberapa tahun ke depan?\u003C\u002Fp>\n\u003Cp>Gimana menurutmu, ngeri atau malah \u003Cem>excited\u003C\u002Fem> nungguin AI yang makin mirip manusia ini?\u003C\u002Fp>\n","",[265,282,295,308,321,326],{"id":266,"title":267,"title_en":21,"slug":268,"excerpt":269,"excerpt_en":21,"has_translation":15,"published_at":270,"reading_time":198,"hidden_from_listing":15,"tags":271,"thumbnail_image":21,"og_image":273,"series":274,"authors":279},133,"Python Strings: the Badge That Only Worked for One Name","python-strings","The badge script printed the right name for the person who wrote it and the wrong name for everybody else. Slicing counts characters, and a name is words.","2026-10-28T13:00:00.000Z",[169,272],"string","\u002Fog\u002Fpython-strings.png",{"id":275,"title":276,"title_en":277,"slug":278},30,"Koleksi dan String","Collections and Strings","python-collections",[280],{"authors_id":281},{"id":74,"name":110,"slug":111,"role":112,"profile_picture":21},{"id":283,"title":284,"title_en":21,"slug":285,"excerpt":286,"excerpt_en":21,"has_translation":15,"published_at":287,"reading_time":198,"hidden_from_listing":15,"tags":288,"thumbnail_image":21,"og_image":290,"series":291,"authors":292},132,"Python Tuples: Why All Three Points Are the Same Point","python-tuples","Three points walk into a loop and come out identical. The list was never copied three times; the name was. A tuple makes that bug impossible.","2026-10-28T12:00:00.000Z",[169,289],"tuple","\u002Fog\u002Fpython-tuples.png",{"id":275,"title":276,"title_en":277,"slug":278},[293],{"authors_id":294},{"id":74,"name":110,"slug":111,"role":112,"profile_picture":21},{"id":296,"title":297,"title_en":21,"slug":298,"excerpt":299,"excerpt_en":21,"has_translation":15,"published_at":300,"reading_time":198,"hidden_from_listing":15,"tags":301,"thumbnail_image":21,"og_image":303,"series":304,"authors":305},131,"Python Sets: the Duplicate That Keeps Coming Back","python-sets","A de-duplication loop that works on clean data leaves four tags where there should be two. The bug is case, and the fix is a `set`.","2026-10-28T11:00:00.000Z",[169,302],"set","\u002Fog\u002Fpython-sets.png",{"id":275,"title":276,"title_en":277,"slug":278},[306],{"authors_id":307},{"id":74,"name":110,"slug":111,"role":112,"profile_picture":21},{"id":309,"title":310,"title_en":21,"slug":311,"excerpt":312,"excerpt_en":21,"has_translation":15,"published_at":313,"reading_time":198,"hidden_from_listing":15,"tags":314,"thumbnail_image":21,"og_image":316,"series":317,"authors":318},130,"Python Dictionaries: the Key That Isn't There","python-dictionary","A word counter dies the first time it meets a word twice. The fix is one line; what takes longer is knowing which of a dict's three lookups to reach for.","2026-10-28T10:00:00.000Z",[169,315],"dictionary","\u002Fog\u002Fpython-dictionary.png",{"id":275,"title":276,"title_en":277,"slug":278},[319],{"authors_id":320},{"id":74,"name":110,"slug":111,"role":112,"profile_picture":21},{"id":231,"title":232,"title_en":233,"slug":234,"excerpt":235,"excerpt_en":236,"has_translation":12,"published_at":237,"reading_time":14,"hidden_from_listing":15,"tags":238,"thumbnail_image":21,"og_image":244,"series":322,"authors":323},{"id":89,"title":35,"title_en":36,"slug":37},[324],{"authors_id":325},{"id":74,"name":110,"slug":111,"role":112,"profile_picture":21},{"id":212,"title":213,"title_en":214,"slug":215,"excerpt":216,"excerpt_en":217,"has_translation":12,"published_at":218,"reading_time":198,"hidden_from_listing":15,"tags":219,"thumbnail_image":21,"og_image":225,"series":327,"authors":328},{"id":89,"title":35,"title_en":36,"slug":37},[329],{"authors_id":330},{"id":74,"name":110,"slug":111,"role":112,"profile_picture":21},[332,335,338,341,344],{"text":333,"depth":96,"id":334},"Jadi, Apa Sebenarnya JEPA Itu?","jadi-apa-sebenarnya-jepa-itu",{"text":336,"depth":96,"id":337},"Gimana Sih Cara Kerjanya? (Spoiler: Anti Perfeksionis!)","gimana-sih-cara-kerjanya-spoiler-anti-perfeksionis",{"text":339,"depth":96,"id":340},"Terus, Kegunaannya Buat Apa Dong?","terus-kegunaannya-buat-apa-dong",{"text":342,"depth":96,"id":343},"Masa Depan JEPA: Jalan Pintas Menuju AI Super Pintar?","masa-depan-jepa-jalan-pintas-menuju-ai-super-pintar",{"text":345,"depth":96,"id":346},"Dari Sekadar \"Ngomong\" Jadi \"Mikir\"","dari-sekadar-ngomong-jadi-mikir",1793295834299]