https://srini-anirudh.github.io/2026-09-01 https://srini-anirudh.github.io/research.html2026-09-01 https://srini-anirudh.github.io/blogs/2026-09-06 https://srini-anirudh.github.io/projects.html2026-09-01 https://srini-anirudh.github.io/about.html2026-09-01 https://srini-anirudh.github.io/blogs/the-agent-evaluation-playbook/2026-09-06 https://srini-anirudh.github.io/blogs/what-autograd-actually-does/2026-03-22 https://srini-anirudh.github.io/blogs/why-transformers-do-not-explode/2026-04-05 https://srini-anirudh.github.io/blogs/choosing-the-next-token/2026-04-19 https://srini-anirudh.github.io/blogs/teaching-a-language-model-to-follow-instructions/2025-08-17 https://srini-anirudh.github.io/blogs/how-lora-changes-a-model-without-rewriting-it/2025-10-12 https://srini-anirudh.github.io/blogs/inside-an-ai-agent-harness/2026-08-02 https://srini-anirudh.github.io/blogs/memory-is-more-than-context/2026-08-09 https://srini-anirudh.github.io/blogs/how-multi-agent-systems-actually-coordinate/2026-08-16 https://srini-anirudh.github.io/blogs/reinforcement-learning-for-agents-from-first-principles/2026-08-30 https://srini-anirudh.github.io/blogs/how-attention-moves-information/2026-02-08 https://srini-anirudh.github.io/blogs/the-puzzle-of-overparameterization/2025-07-06 https://srini-anirudh.github.io/blogs/how-llms-are-pretrained/2026-05-03 https://srini-anirudh.github.io/blogs/mixing-data-without-losing-capabilities/2026-05-10 https://srini-anirudh.github.io/blogs/how-language-models-learn-to-use-tools/2026-06-07 https://srini-anirudh.github.io/blogs/the-making-of-an-ai-agent/2026-06-21 https://srini-anirudh.github.io/blogs/what-changed-inside-the-transformer/2026-06-28 https://srini-anirudh.github.io/blogs/scaling-laws-from-first-principles/2025-10-05 https://srini-anirudh.github.io/blogs/reinforcement-learning-from-first-principles/2025-11-02 https://srini-anirudh.github.io/blogs/teaching-a-model-what-we-prefer/2025-09-14 https://srini-anirudh.github.io/blogs/how-reinforcement-learning-teaches-models-to-reason/2026-04-05 https://srini-anirudh.github.io/blogs/thinking-in-tokens/2025-11-09 https://srini-anirudh.github.io/blogs/how-models-improve-without-changing-their-weights/2025-11-23 https://srini-anirudh.github.io/blogs/how-to-find-what-is-slowing-your-model/2026-06-14 https://srini-anirudh.github.io/blogs/the-serving-playbook/2026-05-10 https://srini-anirudh.github.io/blogs/the-mechanics-of-llm-inference/2026-03-22 https://srini-anirudh.github.io/blogs/the-parallelism-playbook/2026-04-12 https://srini-anirudh.github.io/blogs/inside-a-training-step/2026-03-01 https://srini-anirudh.github.io/blogs/talk-is-not-cheap/2026-02-08 https://srini-anirudh.github.io/blogs/why-fast-gpus-still-wait-for-memory/2026-01-25 https://srini-anirudh.github.io/blogs/why-gpus-are-built-for-deep-learning/2026-01-11 https://srini-anirudh.github.io/blogs/the-vlm-architecture-gallery/2026-08-18 https://srini-anirudh.github.io/blogs/inside-a-modern-vision-encoder/2026-01-18 https://srini-anirudh.github.io/blogs/one-transformer-two-modalities/2026-06-14 https://srini-anirudh.github.io/blogs/an-image-is-a-sentence/2026-05-31 https://srini-anirudh.github.io/blogs/across-the-cnnverse/2026-05-17 https://srini-anirudh.github.io/blogs/evolution-of-ml-architectures/2026-05-03 https://srini-anirudh.github.io/blogs/how-models-know-where-they-are/2026-02-22 https://srini-anirudh.github.io/blogs/what-an-optimizer-actually-does/2026-03-08 https://srini-anirudh.github.io/blogs/the-geometry-of-normalization/2026-01-25 https://srini-anirudh.github.io/blogs/why-neural-networks-need-nonlinearity/2026-01-11