» Tag
ai
39 postsA Production Checklist for Rolling Out Open-Weight AI Models
A practical rollout guide for teams adopting open-weight AI models, covering task contracts, eval sets, routing layers, and output validation.
aiopen-weight-modelsllm-opsai-infrastructureBuilding a Model-Agnostic Vulnerability Discovery Harness
Project Glasswing details a model-agnostic security harness that scans 128 repos across a fleet, avoiding lock-in to any single frontier AI model.
aisecurityllmvulnerability-scanningEncoding Team Standards into AI Instructions
Why senior engineers' tacit knowledge causes inconsistency in AI-assisted development, and how it can be turned into executable, versioned instructions.
aisoftware-engineeringdeveloper-toolscode-reviewAn Ex-Meta Engineer's Guide to Agentic Coding Setup
Ex-Meta/Microsoft/Atlassian principal engineer Kun Chen shares his terminal-centric workflow for managing AI coding agents instead of writing code himself.
aiagentic-engineeringdeveloper-toolsproductivitySensors for tracking maintainability in AI-generated code
An engineer shares how static analysis, testing and security sensors placed across coding, pipeline and production stages help preserve maintainability in AI-generated codebases.
aicode-qualitystatic-analysiseslintProof of Human: A New Way to Verify Real Humans Online
CAPTCHA and phone verification no longer stop bots. The team behind World ID explains how to verify unique humans online without ever revealing who they are.
aibiometricscryptographyidentityWhen AI Agents Orchestrate Agents: The Observability Gap
When AI agents spawn other agents, failures often stay invisible. Sentry's trace-based observability approach reveals exactly which agent introduced the problem.
aiobservabilitymulti-agent-systemssentryAI Inference Engineering: Inside the Prefill-Decode Split
A technical look at how LLM inference splits into compute-bound prefill and memory-bound decode phases, and the optimization techniques engineers use to scale them.
aiinferencellmgpuReading Agent Traces Reveals What Evals Can't Decide
An agent built for AI Engineer World's Fair invented fake speakers. Reading agent traces, not evals, caught it—key lessons on model choice, cost, and observability for engineers.
aiagentsllmobservability