LLM 12
- attestq: When "We Don't Have Evidence for That" Is the Feature
- Giving an AI SOC a Memory: Precedent, Proof, and the Campaigns No Analyst Sees
- langchain-failover Grows a Tier-Split: Gather Cheap, Compose Smart
- detflow Goes Both Ways: From a Threat Report to a Detection Package
- find-evil: Teaching a Forensic Agent to Catch Its Own Hallucinations
- The Day My AI SOC Went Quiet
- detflow: A Detection-Engineering Copilot You Can pip install
- iocflow: Turning a Production AI SOC into a Shippable OSS Library
- SOC-in-a-Box: One LLM, Eight Hats, A Production-Bar AI SOC on a Single GPU
- Three Chat Template Patterns That Silently Kill Your Prompt Cache
- Teaching a Reranker the Language of Security Tickets (+41% MRR@10)
- Why Self-Hosted Claude Code Was 15× Slower Than It Should Be