Llm on Bits, Trades & Systems https://blog.turboawesome.win/tags/llm/ Recent content in Llm on Bits, Trades & Systems Hugo en-us Tue, 19 Aug 2025 09:30:00 +0000 Context Engineering: What the Term Actually Means and What It Doesn't https://blog.turboawesome.win/2025/08/context-engineering-what-the-term-actually-means-and-what-it-doesnt/ Tue, 19 Aug 2025 09:30:00 +0000 https://blog.turboawesome.win/2025/08/context-engineering-what-the-term-actually-means-and-what-it-doesnt/ "Context engineering" became the term of the year in 2025, mostly used to mean nothing. Here is what it actually refers to as an engineering discipline: managing the finite token budget of a model's context window as a resource, with the same rigour you'd apply to memory or a cache. Evaluating LLM-Integrated Systems: What Works and What Doesn't https://blog.turboawesome.win/2025/05/evaluating-llm-integrated-systems-what-works-and-what-doesnt/ Wed, 07 May 2025 11:00:00 +0000 https://blog.turboawesome.win/2025/05/evaluating-llm-integrated-systems-what-works-and-what-doesnt/ LLM outputs are probabilistic and context-dependent. The testing and evaluation approaches from deterministic software don't transfer directly. What does work: eval datasets, LLM-as-judge, regression suites, and the practices that separate teams with confidence from teams flying blind. AI-Native Development: What It Actually Means to Use These Tools Well https://blog.turboawesome.win/2025/03/ai-native-development-what-it-actually-means-to-use-these-tools-well/ Wed, 05 Mar 2025 10:55:00 +0000 https://blog.turboawesome.win/2025/03/ai-native-development-what-it-actually-means-to-use-these-tools-well/ AI coding tools have changed the texture of software development. Not by writing code for you, but by changing what's worth doing yourself and what isn't. A practitioner's view of where the leverage actually is. Building with AI Coding Tools: What Actually Changes and What Doesn't https://blog.turboawesome.win/2025/01/building-with-ai-coding-tools-what-actually-changes-and-what-doesnt/ Wed, 22 Jan 2025 10:08:00 +0000 https://blog.turboawesome.win/2025/01/building-with-ai-coding-tools-what-actually-changes-and-what-doesnt/ A year into using AI coding assistants seriously: what they've changed about how I work, where they still fall short, and the habits that make the difference between AI as a demo and AI as a productivity multiplier. RAG Systems in Production: What the Tutorials Don't Cover https://blog.turboawesome.win/2024/09/rag-systems-in-production-what-the-tutorials-dont-cover/ Wed, 11 Sep 2024 10:44:00 +0000 https://blog.turboawesome.win/2024/09/rag-systems-in-production-what-the-tutorials-dont-cover/ Retrieval-Augmented Generation works well in demos and breaks in interesting ways in production. The gap between 'it answers questions' and 'it reliably answers questions correctly' is where most of the engineering lives. LLM Integration Patterns for Backend Engineers https://blog.turboawesome.win/2024/07/llm-integration-patterns-for-backend-engineers/ Wed, 10 Jul 2024 09:38:00 +0000 https://blog.turboawesome.win/2024/07/llm-integration-patterns-for-backend-engineers/ Integrating LLMs into backend systems requires engineering discipline that the AI ecosystem tutorials often skip. Structured output, function calling, retry strategy, and testing patterns from production. Evaluating LLM Applications: Why 'It Looks Good' Is Not Enough https://blog.turboawesome.win/2024/05/evaluating-llm-applications-why-it-looks-good-is-not-enough/ Tue, 14 May 2024 14:22:00 +0000 https://blog.turboawesome.win/2024/05/evaluating-llm-applications-why-it-looks-good-is-not-enough/ LLM applications fail in ways that traditional software testing doesn't catch. Building evaluation frameworks that give you real signal about quality — before and after deployment — is the engineering challenge that separates serious AI products from demos.