#01Video
AI dijelaskan dalam video singkat
Satu ide per video, dengan bahasa sederhana. Masing-masing terhubung ke bab kursus gratis kami yang menjelaskannya langkah demi langkah.
Mulai di sini AI 101
- #01
#02Machine learning: how a computer draws its own dividing line
#03Neural networks: layers of tiny calculators passing signals on
#04How AI learns: guess, measure the error, nudge, repeat
#05Tokens: how AI chops your words into numbered pieces
#06Embeddings: why a puppy lands closer to a dog than to a pizza
Terbaru
#031Momentum: how remembering past steps stops AI training zigzagging
#030Mini-batches: why AI learns faster from a random handful of data
#029Saddle points: where AI training looks stuck but has a way down
#028Local minima: why AI training can settle for second best
#027Condition number: why a stretched valley makes AI training crawl
#026Learning rate: the step size with a ceiling you can calculate
#025Gradient descent: how AI finds its way downhill in small steps
#024Gradient: the arrow that points uphill, and why AI walks the other way
#023Chain rule: how AI traces the effect of every layer
#022Derivative: how much the result moves when you nudge one input
#021Grid search: why you cannot train an AI by trying every setting
#020Robust loss: stop one wild reading from wrecking your forecast
#019Heavy tails: when rare, huge errors break the usual average
#018Mean squared error: the hidden bet behind squaring your mistakes
#017The LogSumExp trick: one subtraction that stops AI math overflowing
#016Rounding error: why adding the same numbers can give two answers
#015Floating-point numbers: why your computer cannot hold every number
#014Negative log-likelihood: turning a fragile product into a calm sum
#013Maximum likelihood: the answer that makes your data least surprising
#012Bayes' rule: reasoning backwards from a clue to its most likely cause
#011Chain rule of probability: how AI scores a sentence word by word
#010Loss landscape: training an AI means finding the bottom of a valley
#009Loss function: the scoring rule that decides which answer wins
#008Feature engineering: the human choice that can beat the algorithm
Berdasarkan bab kursus
- 1Perceptron dari Nol: Apa yang Dihitung Neuron10 video
- 2Dari Mana Loss Function Berasal: Likelihood, Bukan Konvensi12 video
- 3Menurun: Gradient Descent, dan Dua Langkah yang Selalu Dilewati12 video
- 4Klasifikasi, Cross-Entropy, dan Cara Tidak Menipu Diri Sendiri
- 5Backpropagation dari Nol: Mesin Dulu, Lalu Jaringan1 video
- 6Membuatnya Belajar, Lalu Membuatnya Menggeneralisasi
- 7Bangun BPE Tokenizer: Kenapa Modelmu Tak Bisa Menghitung Huruf R1 video
- 8Prediksi Next-Token: Embeddings, dan Arti Perplexity1 video
- 9Attention dan Blok Transformer, Diturunkan dari Rata-Rata
- 10Pretraining LLM: Data, Komputasi, Scaling Laws, dan Biaya
- 11Dari Base Model ke Assistant: SFT, RLHF, DPO, dan GRPO
- 12Chain of Thought, RLVR, dan Test-Time Compute, diukur
- 13Membuat Inference Murah: KV cache, Batching, dan Kuantisasi
- 14Panggilan LLM Produksi Pertamamu: Streaming, Retry, Timeout
- 15Prompt Engineering, Diukur: Apa yang Mengubah Output
- 16Context Window, Token, dan Tagihan, Terukur
- 17Temperature, Top-p, dan Determinisme yang Sebenarnya Tidak Kamu Punya
- 18Tool Calling dan Structured Outputs: Kontrak yang Tetap Kokoh
- 19RAG di Production: Chunking, Retrieval, dan Sitasi yang Jujur
- 20Fine-Tune, Retrieve, atau Prompt? Keputusannya Ekonomi
- 21Harga Multimodal: Tagihan Nyata untuk Gambar, Audio, dan Video
- 22Apa Itu AI Agent: Lima Tipe Klasik, Dua Definisi yang Bersaing
- 23Membangun Agent Harness: Loop dan Lima Jalan Keluarnya
- 24Context Engineering: Mengapa Agent Kamu Makin Bodoh di Turn 40
- 25Orkestrasi Multi-Agent: Lima Pola, dan Kapan Satu Menang
- 26MCP Dijelaskan Berdasarkan Spesifikasi: Apa Sebenarnya Server Itu
- 27Rilis MCP Server: TypeScript dan Python, Terukur
- 28Agent Skills dan SKILL.md: Progressive Disclosure yang Terukur
- 29Evaluasi LLM: Dari Benchmark Publik ke Golden Set Kamu
- 30Prompt Injection dan Trifecta Mematikan: Mengamankan Agent Nyata