https://piscaries.github.ioNotes on building with LLMs and coding agents https://piscaries.github.io/posts/codex-and-pi-build-the-same-app-in-orca/https://piscaries.github.io/posts/codex-and-pi-build-the-same-app-in-orca/Mon, 05 Oct 2026 00:00:00 +0000Two coding-agent teams, one chess coach, matched conditions. Every review passed both; side by side, the gaps were large. https://piscaries.github.io/posts/can-open-source-coding-agents-build-comparable-software-for/https://piscaries.github.io/posts/can-open-source-coding-agents-build-comparable-software-for/Mon, 03 Aug 2026 00:00:00 +0000Coding agents such as Claude Code and Codex can handle much of the work from planning through testing, but heavy model usage can be expensive. https://piscaries.github.io/posts/rethinking-software-design-principles-for-agent-product/https://piscaries.github.io/posts/rethinking-software-design-principles-for-agent-product/Thu, 23 Apr 2026 00:00:00 +0000Classical principles still hold, but their meaning shifts when the reasoning path is controlled by the model, not the code. https://piscaries.github.io/posts/disrupted-or-defensible-business-models-in-the-llm-era/https://piscaries.github.io/posts/disrupted-or-defensible-business-models-in-the-llm-era/Thu, 12 Jun 2025 00:00:00 +0000While much of the public conversation has focused on workforce disruption, an equally important question has received less attention: https://piscaries.github.io/posts/model-context-protocol-mcp-revolutionizing-software/https://piscaries.github.io/posts/model-context-protocol-mcp-revolutionizing-software/Mon, 17 Mar 2025 00:00:00 +0000The integration of Large Language Models (LLMs) with traditional software systems creates both opportunities and challenges. As AI adoption accelerates, developers need… https://piscaries.github.io/posts/unlocking-the-full-potential-of-rag-systems-avoiding/https://piscaries.github.io/posts/unlocking-the-full-potential-of-rag-systems-avoiding/Sun, 17 Nov 2024 00:00:00 +0000Retrieval-Augmented Generation (RAG) and semantic search are revolutionizing how we harness AI to retrieve and generate knowledge-rich responses. As these transformative… https://piscaries.github.io/posts/practical-guidance-for-evaluating-large-language-model-llm/https://piscaries.github.io/posts/practical-guidance-for-evaluating-large-language-model-llm/Mon, 16 Sep 2024 00:00:00 +0000In today’s data-centric landscape, machine learning (ML) models are crucial for driving decisions, automating processes, and enhancing user experiences across various… https://piscaries.github.io/posts/an-llm-finetuning-use-case-comparing-gemma-and-llama2/https://piscaries.github.io/posts/an-llm-finetuning-use-case-comparing-gemma-and-llama2/Mon, 26 Feb 2024 00:00:00 +0000This article guides you through setting up a local GPU machine for fine-tuning large language models (LLMs), Gemma and Llama2. It presents a case study comparing the two open… https://piscaries.github.io/posts/prototyping-and-comparing-milvus-and-elasticsearch-in/https://piscaries.github.io/posts/prototyping-and-comparing-milvus-and-elasticsearch-in/Sun, 18 Feb 2024 00:00:00 +0000The tech industry has been exploring vector databases primarily due to the rise and increasing importance of machine learning applications. These technologies rely heavily on… https://piscaries.github.io/posts/large-language-model-finetuning-practice/https://piscaries.github.io/posts/large-language-model-finetuning-practice/Tue, 05 Dec 2023 00:00:00 +0000This article demonstrates how to finetune two of the most popular Large Language Models(LLM), OpenAI GPT and Meta Llama2. The main purpose is to demonstrate the step-by-step… https://piscaries.github.io/posts/an-example-of-generating-q-a-training-evaluation-dataset/https://piscaries.github.io/posts/an-example-of-generating-q-a-training-evaluation-dataset/Wed, 29 Nov 2023 00:00:00 +0000The first way is to leverage LangChain’s API. Deeplearning.ai has a great class on LangChain providing a demo generating Q&A on top of OpenAI GPT-3.5. You can get more…