AI signal, minus the noise.

This article presents a hands-on study on generating security operations center (SOC) narratives for insider threat detection using small open-weight language models. The experiments are conducted on the CERT R4.2 dataset using Qwen3 models, comparing four approaches: zero-shot prompting, few-shot prompting, supervised fine-tuning with LoRA (SFT LoRA), and Group Relative Policy Optimization (GRPO). The study demonstrates a practical workflow for adapting small LLMs to explain insider threats, highlighting the accessibility of fine-tuning with open-weight models.

This tutorial provides a practical overview of core LLM concepts for machine learning engineers. It begins with foundational elements like tokens, transformer architectures, and embeddings, then covers advanced techniques including prompt engineering, retrieval-augmented generation (RAG), and fine-tuning. The guide emphasizes developing sound engineering judgment to move beyond trial-and-error prompting. No new research or product announcements are made; it serves as an educational resource.

The provided article excerpt only contains a metaphor comparing a pre-trained model to a professional pianist who can play various music styles. No specific information about fine-tuning methods, steps, or examples is included. The full content is not accessible.

Harness-1 is a 20B retrieval subagent that separates search decisions from bookkeeping by using a stateful harness. It achieves 0.730 average curated recall across eight benchmarks, outperforming other open models and nearing frontier performance. The model is trained with supervised fine-tuning for interface operation and reinforcement learning for search policy, using a finite set of tools and a working memory. Weights and harness code are publicly released on Hugging Face and GitHub.