https://alandao.net/tags/ai/2026-04-06T00:00:00+07:00https://alandao.net/categories/ai/2026-04-06T00:00:00+07:00https://alandao.net/2026-04-06T00:00:00+07:00https://alandao.net/categories/2026-04-06T00:00:00+07:00https://alandao.net/posts/gemma-4-e2b-per-layer-embeddings-ple-research-notes/2026-04-06T00:00:00+07:00https://alandao.net/posts/2026-04-06T00:00:00+07:00https://alandao.net/tags/2026-04-06T00:00:00+07:00https://alandao.net/posts/jan-nano-the-greatest-release-in-my-journey/2025-06-21T22:44:02+07:00https://alandao.net/posts/hcmc-ai-meetup-%231/2025-06-02T09:58:42+07:00https://alandao.net/posts/the-stark-reality-of-ais-reasoning-ability/2025-04-01T15:03:13+07:00https://alandao.net/posts/march-update-things-i-have-done-in-this-quarter/2025-03-15T09:05:26+07:00https://alandao.net/posts/the-imminent-rise-of-openrouter-powered-by-the-ai-code-editor/2025-03-08T11:21:30+07:00https://alandao.net/tags/deepseek/2024-12-29T21:51:59+07:00https://alandao.net/posts/deepseek-v3-is-cool-here-is-why/2024-12-29T21:51:59+07:00https://alandao.net/posts/10-papers-that-caught-my-attention-a-year-in-review/2024-12-21T09:13:03+07:00https://alandao.net/tags/arxiv/2024-12-21T09:13:03+07:00https://alandao.net/tags/papers/2024-12-21T09:13:03+07:00https://alandao.net/tags/science/2024-12-21T09:13:03+07:00https://alandao.net/posts/ultra-compact-text-to-speech-a-quantized-f5tts/2024-12-13T09:30:57+07:00https://alandao.net/tags/career/2024-12-04T12:02:30+07:00https://alandao.net/categories/career/2024-12-04T12:02:30+07:00https://alandao.net/posts/mlops-engineer-a-pragmatic-perspective/2024-12-04T12:02:30+07:00https://alandao.net/posts/paper-summary-what-makes-rope-useful/2024-10-23T21:14:06+07:00https://alandao.net/posts/ichigo-llama-learns-to-talk/2024-10-12T08:43:03+07:00https://alandao.net/tags/llm/2024-08-31T16:24:06+07:00https://alandao.net/posts/tutorial-high-quality-llm-on-low-vram-llama3.1/2024-08-31T16:24:06+07:00https://alandao.net/posts/we-released-a-new-model/2024-08-24T14:48:54+07:00https://alandao.net/posts/the-hidden-cost-of-llm-training-why-optimizers-gulp-down-vram/2024-07-20T21:00:53+07:00https://alandao.net/posts/beyond-the-hype-use-case-driven-ai-development/2024-05-27T20:35:05+07:00https://alandao.net/posts/multi-modal-tokenizing-with-chameleon/2024-05-21T21:54:56+07:00https://alandao.net/posts/rotary-positional-embedding-rope-clearly-explained/2024-05-01T15:54:45+07:00https://alandao.net/posts/eulers-formula-proof/2024-05-01T15:32:17+07:00https://alandao.net/tags/math/2024-05-01T15:32:17+07:00https://alandao.net/posts/ai-in-a-flash-ai-and-the-matrix/2024-04-27T12:41:24+07:00https://alandao.net/about/2024-04-27T00:00:00+00:00https://alandao.net/subscribe/https://alandao.net/subscribe/paid/