/tags/transformers/Recent content in Transformers on Hitesh PattanayakHugoen-usSun, 22 Mar 2026 11:43:37 -0700/posts/the-evolution-beyond-transformers/Sun, 22 Mar 2026 11:43:37 -0700/posts/the-evolution-beyond-transformers/A practical walkthrough of how the Transformer architecture evolved from encoder-decoder to decoder-only models, why attention’s quadratic scaling became a hard wall, and how Mamba’s state space machines are being absorbed into hybrid architectures that dominate production today./posts/training-for-greatness-speed-bleu-records-and-the-multimodal-vision/Sat, 21 Mar 2026 12:20:48 -0700/posts/training-for-greatness-speed-bleu-records-and-the-multimodal-vision/A practical deep-dive into how the original Transformer model shattered translation benchmarks, slashed training costs, and laid the architectural foundation for every major LLM that followed./posts/inside-the-machine-encoders-decoders-and-masking/Sat, 21 Mar 2026 12:19:38 -0700/posts/inside-the-machine-encoders-decoders-and-masking/A practical deep-dive into how the Transformer’s encoder and decoder stacks work, covering residual connections, positional encoding, masked self-attention, and cross-attention with code examples throughout./posts/the-end-of-the-rnn-era-the-query-key-value-revolution/Sat, 21 Mar 2026 12:06:03 -0700/posts/the-end-of-the-rnn-era-the-query-key-value-revolution/A practical walkthrough of why RNNs hit a fundamental wall with sequential processing and long-range dependencies, and how the Query-Key-Value attention mechanism solves both problems in one elegant step.