Meta context engineering beats hand-tuned context
Meta context engineering (ICML 2026) learns the context-engineering process itself, beating ACE-style curation by 18 points while training 13.6x faster.
Context Engineering
All posts
The Wire Blog
Page 3 of 9
Claude Fable 5 put a price on context portability
Claude Fable 5 returns refusals as HTTP 200s and retries them on Opus 4.8. The fallback API reveals exactly what agent context survives a mid-task model swap.
Context Portability
Five criteria of good context for AI agents
A 2026 paper formalizes five criteria for good AI agent context: relevance, sufficiency, isolation, economy, and provenance. Here's how to design for each.
Context Engineering
Sub-agent context isolation: the fix for context rot
Sub-agent context isolation gives each agent its own scoped window, stopping the context rot that kills multi-agent runs. Here's the pattern and its limits.
Multi-Agent System
Claude Opus 4.8 hallucinates less by answering less
Claude Opus 4.8 tops a hallucination benchmark without getting more accurate. It learned to abstain. Why retrieval honesty is a context engineering win.
AI Hallucination
File-native agents: when reading files backfires
A 9,649-experiment study found file-native retrieval lifts frontier-model accuracy 2.7% and drops open-source accuracy 7.7%. Match architecture to the model.
Structured Context
AI notetakers ship the wrong artifact
AI notetakers ship transcripts, but downstream work needs decisions, drafts, or handoffs. The artifact gap is a context engineering problem, not transcription.
Context Engineering
Constraint decay: structural rules break AI coding agents
Constraint decay: AI coding agents lose 30 points of accuracy under architecture and database rules. New EURECOM study explains why and where it hurts most.
AI Agent
Context offloading: 3 patterns for AI agents
Context offloading keeps an AI agent's working context window small by moving state to a destination outside it. Three patterns, and what each one costs.
Context Offloading
Your MCP server is installed. Your agent isn't using it.
Connecting an MCP server is easy. Getting an agent to call its tools on the first relevant turn is where teams lose, and the cause is context.
MCP (Model Context Protocol)