Passionate about AI and software development. This site is my way of giving back — sharing the learnings from my journey, while I keep building and experimenting.https://adityaxblogs.com/en-ushttps://adityaxblogs.com/blogs/self-attention/https://adityaxblogs.com/blogs/self-attention/An intuition-first walk through self attention — queries, keys and values by analogy, then the implementation, multi-head attention, and transformers.Tue, 14 Apr 2026 00:00:00 GMTAILLMTransformersAttentionhttps://adityaxblogs.com/blogs/positional-embeddings/https://adityaxblogs.com/blogs/positional-embeddings/Token embeddings alone throw away word order. How position gets encoded into a sentence, and why the sinusoidal scheme is built the way it is.Sat, 11 Apr 2026 00:00:00 GMTAILLMEmbeddingsTransformershttps://adityaxblogs.com/blogs/token-embeddings/https://adityaxblogs.com/blogs/token-embeddings/How tokens turn into meaningful vectors: the core idea behind embeddings, how the training data is prepared, and a working implementation.Fri, 03 Apr 2026 00:00:00 GMTAILLMEmbeddingshttps://adityaxblogs.com/blogs/neural-networks/https://adityaxblogs.com/blogs/neural-networks/Building a neural network from the ground up — what the layers actually do, how training adjusts them, and a worked example end to end.Sat, 28 Mar 2026 00:00:00 GMTAILLMNeural Networkshttps://adityaxblogs.com/blogs/tokenization/https://adityaxblogs.com/blogs/tokenization/Why models break text into subwords, how Byte Pair Encoding builds a vocabulary from scratch, and what naive word splitting gets wrong.Thu, 19 Mar 2026 00:00:00 GMTAILLMTokenizationhttps://adityaxblogs.com/blogs/llm-in-a-nutshell/https://adityaxblogs.com/blogs/llm-in-a-nutshell/A plain-language overview of how large language models actually work — the mental model worth having before going anywhere near the internals.Fri, 30 Jan 2026 00:00:00 GMTAILLM