https://www.rik-kisnah.ai/tags/llm/Recent content in LLM on Rik Kisnah - BlogHugoenSun, 26 Apr 2026 10:00:00 -0700https://www.rik-kisnah.ai/posts/chat-is-the-product-api-is-the-contract-cli-agents-are-the-harness/Sun, 26 Apr 2026 10:00:00 -0700https://www.rik-kisnah.ai/posts/chat-is-the-product-api-is-the-contract-cli-agents-are-the-harness/1,224 words · 7 min read Disclaimer: This post reflects my personal views and does not represent the views of my employer or my community. Caveat: This was written with research assistance from AI tools, but I curated the content, edited the draft, and cross-checked the references. Image: The illustration above was generated with Gemini. I have done the slow version of AI-assisted coding: paste a failing Python traceback into Claude.https://www.rik-kisnah.ai/posts/a-short-history-of-ai-from-greek-myths-to-large-language-models/Sat, 28 Mar 2026 12:00:00 -0700https://www.rik-kisnah.ai/posts/a-short-history-of-ai-from-greek-myths-to-large-language-models/Disclaimer: This post reflects my personal views and does not represent the views of my employer or my community. Caveat: This was written with research assistance from AI tools, but I curated the content, edited the draft, and cross-checked the references. A Short History of AI: From Greek Myths to Large Language Models Humans have been dreaming up artificial beings for millennia. For example, in Greek myths, Hephaestus was at a forge, creating metal servants.https://www.rik-kisnah.ai/posts/attention-is-all-you-need-and-all-you-need-to-know/Sat, 28 Feb 2026 09:00:00 -0700https://www.rik-kisnah.ai/posts/attention-is-all-you-need-and-all-you-need-to-know/The 2017 Transformer paper replaced sequential processing with parallel attention and launched the GPU infrastructure boom. The same attention problem exists in your repository. Here is how to fix it.https://www.rik-kisnah.ai/posts/how-oci-works-with-oci/Sun, 30 Nov 2025 00:00:00 -0700https://www.rik-kisnah.ai/posts/how-oci-works-with-oci/Disclaimer: This article reflects my personal research and analysis based on publicly available information and is not representative of my employer’s official position. When you type a question into an AI assistant and receive a coherent, contextually relevant response seconds later, something remarkable happens between your keyboard and that reply. For engineers and developers building applications on top of these systems, understanding that process matters. It determines how you architect inference endpoints, allocate GPU resources, and optimize costs.