Building Autonomous
AI Systems
DevOps, Multi-Agent Architecture, Cloud Infrastructure. Production lessons from real systems running in the wild.
Filter by category
02Latest Articles
View allRecursive Language Models: When 8B Beats GPT-5 by Letting Prompts Live in a REPL
002Needle 2: What a 14MB Tool-Calling Model Changes About On-Device Agents
003When Self-Consistency Backfires: Majority Voting Hurts Small LLMs on GPQA Diamond
004AnyDoc and pdf-inspector: Why Firecrawl Open-Sourced Their Rust Document Parsing Stack
005KADATH: The Multi-Agent Runtime That Treats Agent Design Like Evolutionary Search
KADATH appeared in GitHub's fresh-project search with an unusual premise: evolve autonomous agents across reproducible epochs instead of hand-tuning one prompt stack. Its repository is young and its benchmark claims are not yet evidence of general capability, but the runtime exposes a useful design question for systems like ACO: which parts of an agent pipeline should be written by engineers, and which can be searched?
006PHOENIX: Running a Fine-Tuned SLM on a CubeSat Because the Ground Can't Reach It for 85 Minutes
007Activity Frames: The Missing Compiler Between Screen Capture and Agent Memory
008Qwen on Mac in China and U-OPSD: The Quiet Week That Made 8B a Real Product
009Human-in-the-Loop Is Not a Security Boundary: What 40,000 Approvals of AI Agent Commands Actually Show
010Shieldstral: How Mistral Built a 3B Safety Classifier That Outperforms Models 7× Its Size
Mistral's open-weights Shieldstral-1.0-3B collapses safety classification into a single yes/no forward pass with the policy supplied in natural language at inference time, and matches or beats 12B–20B guardrail models on most text and multimodal benchmarks. The post walks through the architecture decision, the 54.1M-sample data construction, the benchmark table, and the vLLM deployment pattern.
011