Building a Local LLM-as-Judge Pipeline for Curating Travel Destination Images
Learn how a local multimodal AI pipeline, lambda architecture, and LLM-as-judge eliminated incorrect place photos in a travel application.
Read the full articleYou might also wanna read
Local vs Cloud LLM: Complete Decision Guide for AI Engineers
Comprehensive framework for choosing between local and cloud LLMs. Cost analysis, capability comparison, and hybrid architecture patterns ba
Local LLM Setup Cost Effective Guide - Run AI Models Without Expensive Hardware
Master cost-effective local LLM deployment using cloud development environments, model quantization, and optimization techniques that make A
Systematic evaluation of 21 LLM-as-a-Judge models reveals reliability flaws and position bias across 541,000 judgments
LLM-as-a-Judge has become the dominant evaluation paradigm for language models, but judge validation in practice relies on exact-match agree
arxiv.org·17d agoSystematic evaluation of 21 LLM-as-a-Judge models reveals reliability flaws and position bias across 541,000 judgments
LLM-as-a-Judge has become the dominant evaluation paradigm for language models, but judge validation in practice relies on exact-match agree
arxiv.org·17d ago
Optimizing Tool Selection for LLM Workflows with Local, Learnable Routers
How local, learnable routers can reduce token overhead, lower costs, and bring structure back to agentic workflows.
viksit.substack.com·1y ago
Running local AI models on an M4 MacBook with 24GB memory: A practical guide
Experiments with getting usable outputs out of local models on a standard Macbook
Johanna Larsson·1mo ago
Mesh-LLM: Distributed LLM Inference System Using llama.cpp Across Multiple Machines
reference impl with llama.cpp compiled to distributed inference across machines, with real end to end demo - michaelneale/mesh-llm
github.com·3mo ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.