Llm on Neat Guy Codinghttps://neatguycoding.com/tags/llm/Recent content in Llm on Neat Guy CodingHugo -- gohugo.ioen© 2026 NeatGuyCodingMon, 18 May 2026 00:00:00 +0000Agentic Topic Modeling: Embedding Pipelines, LLMs, and Human-in-the-Loop Engineering Trade-offshttps://neatguycoding.com/posts/2026-05-18-weaviate-podcast-agentic-topic-modeling-with-maarten-grootendorst-weaviate-podcast-126/Mon, 18 May 2026 00:00:00 +0000https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-agentic-topic-modeling-with-maarten-grootendorst-weaviate-podcast-126/Agentic topic modeling: modular embedding pipelines, LLM-maintained topic tables, and human-in-the-loop granularity—engineering trade-offs between BERTopic, TopicGPT, and retrieval-scale deployment.Compound AI: When a Single LLM Call Is Not Enoughhttps://neatguycoding.com/posts/2026-05-18-weaviate-podcast-compound-ai-systems-with-philip-kiely-weaviate-podcast-105/Mon, 18 May 2026 00:00:00 +0000https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-compound-ai-systems-with-philip-kiely-weaviate-podcast-105/Compound AI: When a single LLM call is not enough—multiple model calls, retrievers, tools, and business logic as a graph; structured output, specialist pipelines, inference stacks, and deployment granularity from a Weaviate podcast with Baseten’s Philip Kiely.Judge-Time Compute: When LLM Evaluation Moves from a Single Score to a Composable Pipelinehttps://neatguycoding.com/posts/2026-05-18-weaviate-podcast-haize-labs-with-leonard-tang-weaviate-podcast-121/Mon, 18 May 2026 00:00:00 +0000https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-haize-labs-with-leonard-tang-weaviate-podcast-121/Judge-time compute: stacking structured, composable weak-model calls at evaluation time instead of assuming one expensive judge pass is enough—Verdict, agreement metrics, and production guardrails, with evidence boundaries called out.Semantic Query Engines: When LLM Operators Enter the Query Optimizerhttps://neatguycoding.com/posts/2026-05-18-weaviate-podcast-semantic-query-engines-with-matthew-russo-weaviate-podcast-131/Mon, 18 May 2026 00:00:00 +0000https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-semantic-query-engines-with-matthew-russo-weaviate-podcast-131/Semantic query engines treat foundation-model filter, join, classify, map, and rank as first-class operators—logical and physical plans, cost–quality tradeoffs, SemBench workloads, and how they differ from script-style RAG and vector search alone.When Format Constraints Hurt LLMs: A Split Between Agent Pipelines and Benchmark Evaluationhttps://neatguycoding.com/posts/2026-05-18-weaviate-podcast-let-me-speak-freely-with-zhi-rui-tam-weaviate-podcast-108/Mon, 18 May 2026 00:00:00 +0000https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-let-me-speak-freely-with-zhi-rui-tam-weaviate-podcast-108/When format constraints hurt LLMs: the same structured-output techniques often lower scores on reasoning tasks and raise them on discrete classification—from agent pipelines to benchmark evaluation.