» Tag
llm
51 postsSubtext Visualizes an LLM's Internal Reasoning in Real Time
Subtext is an open-source tool that applies Anthropic's Jacobian lens to visualize a local LLM's internal representations live during conversation.
llminterpretabilityopen-sourceanthropicBuilding 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-reviewLayer-First Pattern Cuts LLM Overload in Map Generation
RidgeText stores map layers server-side instead of passing raw GeoJSON to the LLM, cutting tool-call context from roughly 125,000 tokens down to about 150.
llmgeojsonmapboxtool-callingScaling LLM Usage with LiteLLM: Monitoring, Quotas and Spend
Midas engineers explain how they built a unified LiteLLM gateway to centralize LLM observability, spend tracking, and per-environment quotas.
llmlitellmobservabilitykubernetesHarness Engineering for Coding Agent Users
A framework for harnessing coding agents: feedforward guides, feedback sensors, and computational vs inferential controls across the development lifecycle.
ai-agentscoding-agentssoftware-qualitydeveloper-toolsWhen 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-systemssentrySlack Speeds Up Security Investigations with a Multi-Agent Architecture
Slack's security engineering team explains how it evolved a simple prompt prototype into a structured multi-agent system with Director, Expert, and Critic roles.
ai-agentssecurityllmincident-responseAI 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