https://www.ahmadosman.com/blog/ Recent content in Blogs on Osman's Odyssey: Byte & Build https://www.ahmadosman.com/logo/byte-and-build.png https://www.ahmadosman.com/logo/byte-and-build.png Hugo -- 0.145.0 en-us Thu, 26 Jun 2025 14:35:54 -0500 https://www.ahmadosman.com/blog/first-came-the-tokenizer/ Thu, 26 Jun 2025 14:35:54 -0500 https://www.ahmadosman.com/blog/first-came-the-tokenizer/ A deep dive into tokenizers, the invisible first piece of your LLM stack. Learn how they control costs, context windows, and performance, and see how algorithms like BPE and SentencePiece can make or break your AI. https://www.ahmadosman.com/blog/learn-llms-roadmap/ Mon, 23 Jun 2025 13:02:02 -0500 https://www.ahmadosman.com/blog/learn-llms-roadmap/ The straight-up, no-BS roadmap for learning LLMs in 2025. Skip the ML fluff and endless prerequisites. Get the actionable phases, projects, and resources to actually build, train, and ship large language models—from the ground up. https://www.ahmadosman.com/blog/software-engineers-arent-getting-automated-local-ai-has-to-win/ Sat, 21 Jun 2025 07:08:00 -0500 https://www.ahmadosman.com/blog/software-engineers-arent-getting-automated-local-ai-has-to-win/ Stop worrying about AI replacing you—the real threat is losing technical depth. As cloud dependence grows and platforms get more opaque, local-first AI, open weights, and full-stack ownership are the only safety nets left. Why the future belongs to those who can build, debug, and own their tools from the metal up. Trust no corporate overlord. https://www.ahmadosman.com/blog/my-ultimate-deepresearch-prompt-builder/ Fri, 20 Jun 2025 03:06:06 -0500 https://www.ahmadosman.com/blog/my-ultimate-deepresearch-prompt-builder/ I’m sharing my DeepResearch prompt builder template—the system that powers my research and learning workflows. Learn exactly how I turn chaos into clarity, force actionable insights, and get the most out of LLMs. See the template, my step-by-step process, and real-world tips for DeepResearchMaxxing in 2025. https://www.ahmadosman.com/blog/just-like-gpus-we-need-to-be-stress-tested-101-days-of-blogging/ Wed, 18 Jun 2025 23:02:02 -0500 https://www.ahmadosman.com/blog/just-like-gpus-we-need-to-be-stress-tested-101-days-of-blogging/ Why 101 days of daily tech blogging? A raw, open challenge on AI, LLMs, self-hosted experiments, knowledge distillation, and why consistency beats talent. Expect rants, technical breakdowns, open hardware journeys, memes, and daily accountability from the basement AI server guy. https://www.ahmadosman.com/blog/mastering-the-corporate-game-space/ Fri, 02 May 2025 14:44:44 -0500 https://www.ahmadosman.com/blog/mastering-the-corporate-game-space/ Corporate politics isn't just backroom deals—it's how influence, visibility, and relationships shape your career. In this candid guide, you'll learn to use titles, politics, and intentional networking to your advantage (without selling your soul). Real talk from people who've played—and won—the game at big tech and beyond. https://www.ahmadosman.com/blog/once-undesirable-now-undeniable/ Wed, 30 Apr 2025 15:46:46 -0500 https://www.ahmadosman.com/blog/once-undesirable-now-undeniable/ How taking risks, building in public, and refusing to play a losing game flipped the script—and why sometimes you have to become undeniable before you ever become accepted. https://www.ahmadosman.com/blog/build-your-local-privat-ai-screenshot-organizer-with-lmstudio/ Tue, 22 Apr 2025 08:56:56 -0500 https://www.ahmadosman.com/blog/build-your-local-privat-ai-screenshot-organizer-with-lmstudio/ Build a local, privacy-first screenshot organizer using LMStudio’s Python SDK and Gemma 3 multimodal models. Keep your data off the cloud, automate screenshot categorization, and leverage the power of open-source AI—all running from your own PC. Step-by-step guide, code walkthrough, and a practical use-case for local LLMs. https://www.ahmadosman.com/blog/no-rag-is-not-dead-space/ Fri, 11 Apr 2025 15:31:31 -0500 https://www.ahmadosman.com/blog/no-rag-is-not-dead-space/ Forget the hype—here’s what actually happened when we asked “Is RAG dead?” This deep-dive explores why Retrieval-Augmented Generation (RAG) is still essential in real AI systems, what people get wrong, and how practitioners are shipping the next wave of AI with smarter retrieval, dynamic context, and hard-earned lessons from the field. https://www.ahmadosman.com/blog/from-the-shadows-to-the-feed/ Tue, 25 Mar 2025 14:28:28 -0500 https://www.ahmadosman.com/blog/from-the-shadows-to-the-feed/ After years of building in the dark, I decided to play the game of distribution. Here’s why networks—and distribution—matter more than ever, and why I’m finally sharing my journey, experiments, and ideas in public. https://www.ahmadosman.com/blog/r1-ktransformers-inference-livestream/ Fri, 14 Feb 2025 02:56:56 -0600 https://www.ahmadosman.com/blog/r1-ktransformers-inference-livestream/ Key takeaways from livestreaming DeepSeek R-1 671B (4-bit) on a 14x RTX 3090 basement AI server. See how KTransformers crushed llama.cpp in prompt eval speeds, compare setups, and get real-world insights into massive LLM inference with vLLM, ExLlamaV2, and more. https://www.ahmadosman.com/blog/do-not-use-llama-cpp-or-ollama-on-multi-gpus-setups-use-vllm-or-exllamav2/ Fri, 07 Feb 2025 05:06:36 -0600 https://www.ahmadosman.com/blog/do-not-use-llama-cpp-or-ollama-on-multi-gpus-setups-use-vllm-or-exllamav2/ Exploring the intricacies of Inference Engines and why llama.cpp should be avoided when running Multi-GPU setups. Learn about Tensor Parallelism, the role of vLLM in batch inference, and why ExLlamaV2 has been a game-changer for GPU-optimized AI serving since it introduced Tensor Parallelism. https://www.ahmadosman.com/blog/deepseek-r1-space/ Sun, 02 Feb 2025 15:35:35 -0600 https://www.ahmadosman.com/blog/deepseek-r1-space/ A curated collection of links, books, tools, and benchmarks discussed during the February 2nd, 2025 Twitter/X Audio Space on LLMs and AI. Includes practical resources, RAG leaderboards, toolkits, and perspectives on AI adoption in the Middle East and globally. https://www.ahmadosman.com/blog/taleb-antifragile-ai-insights/ Tue, 03 Dec 2024 04:21:55 -0600 https://www.ahmadosman.com/blog/taleb-antifragile-ai-insights/ Explore how AI systems can become antifragile, harnessing uncertainty to thrive. Learn about the shift and acceleration from traditional software to AI agentic systems and their implications for the future. https://www.ahmadosman.com/blog/go-all-in/ Tue, 01 Oct 2024 22:08:52 -0500 https://www.ahmadosman.com/blog/go-all-in/ Embrace new ideas, trust your instincts, and go all in. 42 days to launch—let’s win this game! #GoAllIn https://www.ahmadosman.com/blog/serving-ai-from-the-basement-part-ii/ Wed, 18 Sep 2024 05:57:26 -0500 https://www.ahmadosman.com/blog/serving-ai-from-the-basement-part-ii/ SWE Agentic Framework, MoEs, Quantizations & Mixed Precision, Batch Inference, LLM Architectures, vLLM, DeepSeek v2.5, Embedding Models, and Speculative Decoding: An LLM Brain Dump... I have been working on a multi-agent system that simulates a team of Software Engineers; this system assigns projects, creates teams and adds members to them based on areas of expertise and need, and asks team members to build features, assign story points, have pair programming sessions together, etc. https://www.ahmadosman.com/blog/serving-ai-from-the-basement-part-i/ Fri, 06 Sep 2024 16:37:23 -0500 https://www.ahmadosman.com/blog/serving-ai-from-the-basement-part-i/ Dedicated LLM server powered by 8x RTX 3090 Graphic Cards, boasting a total of 192GB of VRAM.