[{"data":1,"prerenderedAt":349},["ShallowReactive",2],{"tag-labels":3,"site-header":4,"article-kenapa-ai-suka-halu-dan-gimana-jepa-beresin-masalah-ini-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":264,"renderedTakeaway":265,"latestArticles":266,"toc":333},{"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":260,"available_locales":261,"body":263,"takeway":21,"prerequisite":21},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",4,[83,84,85,86],"artificial-intelligence","jepa","world-models","yann-lecun","\u002Fog\u002Fkenapa-ai-suka-halu-dan-gimana-jepa-beresin-masalah-ini.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.",[92,105,123,128,142,156,173,190,211,230],{"id":93,"title":94,"title_en":95,"slug":96,"excerpt":97,"excerpt_en":98,"has_translation":12,"published_at":99,"reading_time":81,"hidden_from_listing":15,"tags":100,"thumbnail_image":21,"og_image":102,"series":103,"authors":104},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",[84,83,86,101],"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},[],{"id":106,"title":107,"title_en":108,"slug":109,"excerpt":110,"excerpt_en":111,"has_translation":12,"published_at":112,"reading_time":81,"hidden_from_listing":15,"tags":113,"thumbnail_image":21,"og_image":115,"series":116,"authors":117},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",[83,114,86,84],"llm","\u002Fog\u002Fllm-bakal-mentok-terus-gimana-dong.png",{"id":89,"title":35,"title_en":36,"slug":37},[118],{"authors_id":119},{"id":93,"name":120,"slug":121,"role":122,"profile_picture":21},"Daffa Izzuddin","izzudd","Writer",{"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":124,"authors":125},{"id":89,"title":35,"title_en":36,"slug":37},[126],{"authors_id":127},{"id":93,"name":120,"slug":121,"role":122,"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",[84,86,136,101],"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":93,"name":120,"slug":121,"role":122,"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",[84,150],"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":93,"name":120,"slug":121,"role":122,"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",[165,166,167,114,168,169],"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,[183,114,168,184],"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":93,"name":120,"slug":121,"role":122,"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":93,"name":120,"slug":121,"role":122,"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",[220,221,222,223,224,114],"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":93,"name":120,"slug":121,"role":122,"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":93,"name":120,"slug":121,"role":122,"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,[258],{"authors_id":259},{"id":93,"name":120,"slug":121,"role":122,"profile_picture":21},"id",[262,260],"en","\nKalian sadar nggak sih, AI zaman sekarang tuh emang makin jago. Mau disuruh nulis kode, bikin puisi, sampai *generate* gambar super realistis, semuanya dilibas. Tapi di balik semua kecerdasannya, AI sering banget bikin kesalahan yang kalau dipikir pakai logika manusia tuh konyol banget.\n\nPernah kan minta AI bikin gambar orang lagi makan, eh yang muncul malah tangan dengan tujuh jari atau garpu yang menyatu sama bibir? Atau AI teks yang dengan santainya nyuruh kita pakai lem biar keju bisa nempel di pizza? Masalah ini utamanya muncul di model model lawas atau model yang ukurannya kecil.\n\nSecara logika fisik, itu jelas ngawur. Masalah utamanya cuma satu: AI saat ini nggak punya *common sense* atau \"akal sehat\". Mereka nggak beneran paham gimana dunia nyata ini bekerja dan cuma nebak-nebak probabilitas kata atau piksel selanjutnya berdasarkan data hafalan.\n\nNah, buat ngakalin jalan buntu ini, muncul arsitektur baru namanya **JEPA (Joint-Embedding Predictive Architecture)**. Dikembangkan dari visi Yann LeCun di Meta, JEPA ini bukan sekadar model AI biasa. Ini adalah pondasi baru biar mesin bisa beneran ngerti realita. Yuk, kita bedah pelan-pelan kenapa JEPA ini bakal jadi *game changer*!\n\n## Kenapa AI Generatif Masih Sering \"Halu\"?\n\nCoba deh perhatiin balita atau kucing peliharaan kalian di rumah pas lagi iseng nyenggol gelas di pinggir meja. Begitu gelasnya jatuh dan pecah, mereka langsung belajar satu hukum fisika dasar: barang itu jatuhnya ke bawah, dan kalau dari kaca pasti pecah. Mereka cuma butuh ngelihat kejadian itu sekali dua kali buat paham konsepnya seumur hidup.\n\nBandingin sama AI yang ada sekarang. Mereka terlalu manja sama data. AI butuh disuapi jutaan video gelas jatuh yang udah dilabeli sama manusia baru bisa paham konsep \"jatuh\". Belum lagi AI yang dilatih pakai metode *trial and error* untuk main *game*; mereka butuh nabrak tembok ribuan kali dulu sampai akhirnya sadar kalau tembok itu keras.\n\nKemampuan \"mengamati dan langsung paham\" layaknya makhluk hidup inilah yang selama ini hilang dari AI, dan sekarang pelan-pelan mulai ditanamkan ke dalam JEPA.\n\n## Simulasi Masa Depan Lewat *World Models*\n\nIde paling brilian dari JEPA ada di kemampuannya buat ngebangun *World Models* atau model dunia. Gampangnya, ini tuh semacam simulasi mental di dalam \"kepala\" AI tentang gimana dunia ini berjalan.\n\nPas kalian mau nyebrang jalan raya yang lagi rame, otak kalian nggak mungkin pasrah jalan maju terus baru mundur pas ketabrak motor, kan? Secara otomatis, otak kita ngelakuin simulasi masa depan: *\"Wah, kalau aku nyebrang sekarang dengan kecepatan segini, dan motor di sana ngebut gitu, bisa ketabrak nih. Mending nunggu lima detik lagi.\"*\n\nJEPA ngajarin AI untuk punya kemampuan meramal kayak gitu. Alih-alih bereaksi buta, AI bisa mensimulasikan berbagai skenario di kepalanya, menimbang akibatnya, lalu ngerencanain tindakan yang paling aman. Persis kayak cara kita mikir sebelum nyebrang jalan.\n\n## Berhenti Pusing Mikirin Piksel, Mulai Fokus ke Inti\n\nAda satu perbedaan filosofis yang lumayan kerasa antara JEPA sama AI video atau gambar yang beredar sekarang. AI generatif itu ibaratnya terlalu perfeksionis, tapi malah jadi kurang pintar.\n\nBayangin aja ada AI yang disuruh memprediksi kelanjutan video mobil yang lagi melaju di jalanan dengan *background* pohon rindang. Kalau AI biasa, dia bakal ngabisin komputasi buat nebak ke arah mana ribuan helai daun di pohon itu bakal tertiup angin. Padahal arah daun itu kan acak dan sama sekali nggak penting buat cerita utamanya.\n\nDi sinilah JEPA milih jalan yang jauh lebih elegan. Dia nggak peduli sama piksel demi piksel. JEPA sengaja \"menutup mata\" pada detail remah-remah kayak arah daun atau pantulan cahaya di kaca spion, dan cuma fokus pada representasi abstraknya: *mobil ini bergerak maju dua meter*.\n\nPemahaman akan \"esensi\" inilah yang jadi cikal bakal akal sehat. AI nggak lagi terjebak di detail visual, tapi bener-bener fokus ke hukum sebab-akibat.\n\n## Mikir Jangka Panjang dengan H-JEPA\n\nNgomong-ngomong soal rencana, manusia itu kalau bikin rencana pasti bertahap. Dari yang sifatnya abstrak banget sampai ke hal-hal teknis.\n\nMisalnya nih, kalian lagi laper dan pengen masak mi instan pakai telur. Tujuan besarnya kan itu, abstrak dan jangka panjang. Begitu tujuannya udah dikunci, baru deh otak kalian nurunin perintah jadi hal-hal teknis: *nyalain kompor, tuang air ke panci, masukin mi.* JEPA juga punya mekanisme buat meniru alur berpikir ini lewat **Hierarchical JEPA (H-JEPA)**. Di tingkat pikiran yang paling atas, AI bikin rencana jangka panjang. Nanti, rencana besar ini bakal ngasih \"perintah\" ke level di bawahnya yang ngurusin hal-hal teknis, misalnya ngasih instruksi ke tangan robot buat muter knop kompor. Semuanya jalan mulus secara hierarkis tanpa bikin mesinnya pusing mikirin semuanya dalam satu waktu.\n\n## Masa Depan?\n\nKehadiran JEPA ngasih kita pandangan yang lebih masuk akal soal masa depan kecerdasan buatan. Lewat *World Models* dan pemahaman konsep yang abstrak, kita akhirnya pelan-pelan berhenti ngajarin AI untuk sekadar jadi \"burung beo\" penebak kata, dan mulai ngebangun AI yang beneran paham hukum fisika di dunia nyata.\n\nDengan ngasih AI kemampuan buat ngebayangin masa depan, mengenali bahaya sebelum bertindak, dan bikin rencana bertahap, JEPA ngebawa kita selangkah lebih deket ke mesin yang punya akal sehat sejati.\n\nMemang sih, AI dengan pemahaman setara manusia nggak bakal muncul besok pagi. Tapi berkat arsitektur kayak gini, pondasinya udah mulai kebentuk. Gimana menurut kalian? Kira-kira hal apa yang bakal paling berubah kalau AI masa depan beneran udah punya \"akal sehat\" dan nggak gampang halu lagi?\n","\u003Cp>Kalian sadar nggak sih, AI zaman sekarang tuh emang makin jago. Mau disuruh nulis kode, bikin puisi, sampai \u003Cem>generate\u003C\u002Fem> gambar super realistis, semuanya dilibas. Tapi di balik semua kecerdasannya, AI sering banget bikin kesalahan yang kalau dipikir pakai logika manusia tuh konyol banget.\u003C\u002Fp>\n\u003Cp>Pernah kan minta AI bikin gambar orang lagi makan, eh yang muncul malah tangan dengan tujuh jari atau garpu yang menyatu sama bibir? Atau AI teks yang dengan santainya nyuruh kita pakai lem biar keju bisa nempel di pizza? Masalah ini utamanya muncul di model model lawas atau model yang ukurannya kecil.\u003C\u002Fp>\n\u003Cp>Secara logika fisik, itu jelas ngawur. Masalah utamanya cuma satu: AI saat ini nggak punya \u003Cem>common sense\u003C\u002Fem> atau "akal sehat". Mereka nggak beneran paham gimana dunia nyata ini bekerja dan cuma nebak-nebak probabilitas kata atau piksel selanjutnya berdasarkan data hafalan.\u003C\u002Fp>\n\u003Cp>Nah, buat ngakalin jalan buntu ini, muncul arsitektur baru namanya \u003Cstrong>JEPA (Joint-Embedding Predictive Architecture)\u003C\u002Fstrong>. Dikembangkan dari visi Yann LeCun di Meta, JEPA ini bukan sekadar model AI biasa. Ini adalah pondasi baru biar mesin bisa beneran ngerti realita. Yuk, kita bedah pelan-pelan kenapa JEPA ini bakal jadi \u003Cem>game changer\u003C\u002Fem>!\u003C\u002Fp>\n\u003Ch2 id=\"kenapa-ai-generatif-masih-sering-halu\">Kenapa AI Generatif Masih Sering "Halu"?\u003C\u002Fh2>\n\u003Cp>Coba deh perhatiin balita atau kucing peliharaan kalian di rumah pas lagi iseng nyenggol gelas di pinggir meja. Begitu gelasnya jatuh dan pecah, mereka langsung belajar satu hukum fisika dasar: barang itu jatuhnya ke bawah, dan kalau dari kaca pasti pecah. Mereka cuma butuh ngelihat kejadian itu sekali dua kali buat paham konsepnya seumur hidup.\u003C\u002Fp>\n\u003Cp>Bandingin sama AI yang ada sekarang. Mereka terlalu manja sama data. AI butuh disuapi jutaan video gelas jatuh yang udah dilabeli sama manusia baru bisa paham konsep "jatuh". Belum lagi AI yang dilatih pakai metode \u003Cem>trial and error\u003C\u002Fem> untuk main \u003Cem>game\u003C\u002Fem>; mereka butuh nabrak tembok ribuan kali dulu sampai akhirnya sadar kalau tembok itu keras.\u003C\u002Fp>\n\u003Cp>Kemampuan "mengamati dan langsung paham" layaknya makhluk hidup inilah yang selama ini hilang dari AI, dan sekarang pelan-pelan mulai ditanamkan ke dalam JEPA.\u003C\u002Fp>\n\u003Ch2 id=\"simulasi-masa-depan-lewat-world-models\">Simulasi Masa Depan Lewat \u003Cem>World Models\u003C\u002Fem>\u003C\u002Fh2>\n\u003Cp>Ide paling brilian dari JEPA ada di kemampuannya buat ngebangun \u003Cem>World Models\u003C\u002Fem> atau model dunia. Gampangnya, ini tuh semacam simulasi mental di dalam "kepala" AI tentang gimana dunia ini berjalan.\u003C\u002Fp>\n\u003Cp>Pas kalian mau nyebrang jalan raya yang lagi rame, otak kalian nggak mungkin pasrah jalan maju terus baru mundur pas ketabrak motor, kan? Secara otomatis, otak kita ngelakuin simulasi masa depan: \u003Cem>"Wah, kalau aku nyebrang sekarang dengan kecepatan segini, dan motor di sana ngebut gitu, bisa ketabrak nih. Mending nunggu lima detik lagi."\u003C\u002Fem>\u003C\u002Fp>\n\u003Cp>JEPA ngajarin AI untuk punya kemampuan meramal kayak gitu. Alih-alih bereaksi buta, AI bisa mensimulasikan berbagai skenario di kepalanya, menimbang akibatnya, lalu ngerencanain tindakan yang paling aman. Persis kayak cara kita mikir sebelum nyebrang jalan.\u003C\u002Fp>\n\u003Ch2 id=\"berhenti-pusing-mikirin-piksel-mulai-fokus-ke-inti\">Berhenti Pusing Mikirin Piksel, Mulai Fokus ke Inti\u003C\u002Fh2>\n\u003Cp>Ada satu perbedaan filosofis yang lumayan kerasa antara JEPA sama AI video atau gambar yang beredar sekarang. AI generatif itu ibaratnya terlalu perfeksionis, tapi malah jadi kurang pintar.\u003C\u002Fp>\n\u003Cp>Bayangin aja ada AI yang disuruh memprediksi kelanjutan video mobil yang lagi melaju di jalanan dengan \u003Cem>background\u003C\u002Fem> pohon rindang. Kalau AI biasa, dia bakal ngabisin komputasi buat nebak ke arah mana ribuan helai daun di pohon itu bakal tertiup angin. Padahal arah daun itu kan acak dan sama sekali nggak penting buat cerita utamanya.\u003C\u002Fp>\n\u003Cp>Di sinilah JEPA milih jalan yang jauh lebih elegan. Dia nggak peduli sama piksel demi piksel. JEPA sengaja "menutup mata" pada detail remah-remah kayak arah daun atau pantulan cahaya di kaca spion, dan cuma fokus pada representasi abstraknya: \u003Cem>mobil ini bergerak maju dua meter\u003C\u002Fem>.\u003C\u002Fp>\n\u003Cp>Pemahaman akan "esensi" inilah yang jadi cikal bakal akal sehat. AI nggak lagi terjebak di detail visual, tapi bener-bener fokus ke hukum sebab-akibat.\u003C\u002Fp>\n\u003Ch2 id=\"mikir-jangka-panjang-dengan-h-jepa\">Mikir Jangka Panjang dengan H-JEPA\u003C\u002Fh2>\n\u003Cp>Ngomong-ngomong soal rencana, manusia itu kalau bikin rencana pasti bertahap. Dari yang sifatnya abstrak banget sampai ke hal-hal teknis.\u003C\u002Fp>\n\u003Cp>Misalnya nih, kalian lagi laper dan pengen masak mi instan pakai telur. Tujuan besarnya kan itu, abstrak dan jangka panjang. Begitu tujuannya udah dikunci, baru deh otak kalian nurunin perintah jadi hal-hal teknis: \u003Cem>nyalain kompor, tuang air ke panci, masukin mi.\u003C\u002Fem> JEPA juga punya mekanisme buat meniru alur berpikir ini lewat \u003Cstrong>Hierarchical JEPA (H-JEPA)\u003C\u002Fstrong>. Di tingkat pikiran yang paling atas, AI bikin rencana jangka panjang. Nanti, rencana besar ini bakal ngasih "perintah" ke level di bawahnya yang ngurusin hal-hal teknis, misalnya ngasih instruksi ke tangan robot buat muter knop kompor. Semuanya jalan mulus secara hierarkis tanpa bikin mesinnya pusing mikirin semuanya dalam satu waktu.\u003C\u002Fp>\n\u003Ch2 id=\"masa-depan\">Masa Depan?\u003C\u002Fh2>\n\u003Cp>Kehadiran JEPA ngasih kita pandangan yang lebih masuk akal soal masa depan kecerdasan buatan. Lewat \u003Cem>World Models\u003C\u002Fem> dan pemahaman konsep yang abstrak, kita akhirnya pelan-pelan berhenti ngajarin AI untuk sekadar jadi "burung beo" penebak kata, dan mulai ngebangun AI yang beneran paham hukum fisika di dunia nyata.\u003C\u002Fp>\n\u003Cp>Dengan ngasih AI kemampuan buat ngebayangin masa depan, mengenali bahaya sebelum bertindak, dan bikin rencana bertahap, JEPA ngebawa kita selangkah lebih deket ke mesin yang punya akal sehat sejati.\u003C\u002Fp>\n\u003Cp>Memang sih, AI dengan pemahaman setara manusia nggak bakal muncul besok pagi. Tapi berkat arsitektur kayak gini, pondasinya udah mulai kebentuk. Gimana menurut kalian? Kira-kira hal apa yang bakal paling berubah kalau AI masa depan beneran udah punya "akal sehat" dan nggak gampang halu lagi?\u003C\u002Fp>\n","",[267,284,297,310,323,328],{"id":268,"title":269,"title_en":21,"slug":270,"excerpt":271,"excerpt_en":21,"has_translation":15,"published_at":272,"reading_time":198,"hidden_from_listing":15,"tags":273,"thumbnail_image":21,"og_image":275,"series":276,"authors":281},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",[169,274],"string","\u002Fog\u002Fpython-strings.png",{"id":277,"title":278,"title_en":279,"slug":280},30,"Koleksi dan String","Collections and Strings","python-collections",[282],{"authors_id":283},{"id":93,"name":120,"slug":121,"role":122,"profile_picture":21},{"id":285,"title":286,"title_en":21,"slug":287,"excerpt":288,"excerpt_en":21,"has_translation":15,"published_at":289,"reading_time":198,"hidden_from_listing":15,"tags":290,"thumbnail_image":21,"og_image":292,"series":293,"authors":294},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",[169,291],"tuple","\u002Fog\u002Fpython-tuples.png",{"id":277,"title":278,"title_en":279,"slug":280},[295],{"authors_id":296},{"id":93,"name":120,"slug":121,"role":122,"profile_picture":21},{"id":298,"title":299,"title_en":21,"slug":300,"excerpt":301,"excerpt_en":21,"has_translation":15,"published_at":302,"reading_time":198,"hidden_from_listing":15,"tags":303,"thumbnail_image":21,"og_image":305,"series":306,"authors":307},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",[169,304],"set","\u002Fog\u002Fpython-sets.png",{"id":277,"title":278,"title_en":279,"slug":280},[308],{"authors_id":309},{"id":93,"name":120,"slug":121,"role":122,"profile_picture":21},{"id":311,"title":312,"title_en":21,"slug":313,"excerpt":314,"excerpt_en":21,"has_translation":15,"published_at":315,"reading_time":198,"hidden_from_listing":15,"tags":316,"thumbnail_image":21,"og_image":318,"series":319,"authors":320},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",[169,317],"dictionary","\u002Fog\u002Fpython-dictionary.png",{"id":277,"title":278,"title_en":279,"slug":280},[321],{"authors_id":322},{"id":93,"name":120,"slug":121,"role":122,"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":324,"authors":325},{"id":89,"title":35,"title_en":36,"slug":37},[326],{"authors_id":327},{"id":93,"name":120,"slug":121,"role":122,"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":329,"authors":330},{"id":89,"title":35,"title_en":36,"slug":37},[331],{"authors_id":332},{"id":93,"name":120,"slug":121,"role":122,"profile_picture":21},[334,337,340,343,346],{"text":335,"depth":106,"id":336},"Kenapa AI Generatif Masih Sering \"Halu\"?","kenapa-ai-generatif-masih-sering-halu",{"text":338,"depth":106,"id":339},"Simulasi Masa Depan Lewat World Models","simulasi-masa-depan-lewat-world-models",{"text":341,"depth":106,"id":342},"Berhenti Pusing Mikirin Piksel, Mulai Fokus ke Inti","berhenti-pusing-mikirin-piksel-mulai-fokus-ke-inti",{"text":344,"depth":106,"id":345},"Mikir Jangka Panjang dengan H-JEPA","mikir-jangka-panjang-dengan-h-jepa",{"text":347,"depth":106,"id":348},"Masa Depan?","masa-depan",1793295834278]