harness
30 articles about harness in AI news
Claude Code's Harness Wins by 23.8 Points
Claude Code's harness—maximal tools, context caching, and subagent orchestration—drives a 23.8-point performance gap. Use CLAUDE.md and /compact to optimize your context window.
DeepSeek Open-Sources Harness (dsh) With Plugin Architecture
DeepSeek open-sourced DeepSeek Harness, a plugin-based agent harness that crossed 35k GitHub stars in hours. It treats adapters, tools, and session logs as swappable plugins, addressing context-assembly pain points.
Meta: Agent Harness Authoring Still Manual—Automation Gap
Meta research says agent harnesses are mostly hand-authored, limiting robustness. The field needs automated harness tuning to scale agents.
OpenAI hits 38.3% on ARC-AGI-3 with custom API, bypassing official harness
OpenAI's GPT-5.6 Sol scored 38.3% on ARC-AGI-3 with custom API settings, beating Opus 5's 30.2%, but scored 7.8% in the official harness, exposing benchmark parity issues.
Open-Source Course Shows Harness, Not Model, Lifts Coding Agent 25 Places
Open-source course shows harness engineering, not model swap, moved a coding agent from ~30th to top 5 on Terminal-Bench. Course builds Decode from scratch.
Lilian Weng Argues Harness Design, Not Model Rewrites, Is Path to RSI
Lilian Weng argues RSI starts with harness design, not model rewrites, citing Sakana AI's The AI Scientist in Nature 2026 and two other projects.
Stop Dumping Instructions Into CLAUDE.md — Use the 3-Layer Agent Harness
Stop appending rules to CLAUDE.md. Use the 3-Layer Agent Harness: a short constitution (CLAUDE.md), specialist skills, and subagents. This respects the 150-instruction compliance budget and keeps your agent reliable.
5 Harness Internals That Changed How I Use Claude Code Daily
Rebuilding Claude Code's harness reveals that CLAUDE.md layers on a hidden base prompt, hooks can block tool calls, and subagents need abort trees—5 actionable takeaways for daily use.
Stanford, Meta 'Code as Agent Harness' Paper Rethinks AI Agent Design
Stanford and Meta's "Code as Agent Harness" paper proposes code-driven AI agent orchestration, potentially improving reliability over natural language prompts.
Meta-Stanford Survey: Code as Agent Harness Improves AI Reasoning
Meta, Stanford, Illinois survey argues AI agents work better with code as their main working layer, calling it an agent harness.
Code-as-Agent Harness Thesis: 88.5% Gains Without Touching the LLM
Paper shows 88.5% improvement by adapting runtime interface around frozen LLM. Harness generalizes across 18 backbones, challenging model-centric agent improvement.
Claude Code's Six-Layer Architecture: Harness, Not Magic
Claude Code's six-layer architecture uses a 3-layer context compressor at 92% threshold and Redis-based multi-agent FSM protocol. The model is just one node in a harness.
Agentic Harness Engineering Boosts Coding Agents 7% on Terminal-Bench 2
Agentic Harness Engineering introduces a structured approach to evolving coding-agent harnesses, using revertible components, condensed experience, and falsifiable decisions. On Terminal-Bench 2, pass@1 climbs from 69.7% to 77.0% in ten iterations, beating human-designed baselines.
Agent Harnessing: The Infrastructure That Makes AI Agents Work
A detailed technical guide argues that the model is not the hard part of building AI agents. The six-component harness — context management, memory, tools, control flow, verification, and coordination — is what separates production-grade agents from those that fail silently.
Your AI Agent Is Only as Good as Its Harness — Here’s What That Means
An article from Towards AI emphasizes that the reliability and safety of an AI agent depend more on its controlling 'harness'—the system of protocols, tools, and observability layers—than on the underlying model. This concept is reportedly worth $2 billion but remains poorly understood by many developers.
Google Gemini's UI Harness Lags Behind Claude, GPT, Analyst Says
AI researcher Ethan Mollick notes the Gemini Pro 3.1 model is technically capable but hampered by a minimal user interface and tool harness, widening its gap with competitors Claude and ChatGPT.
Akshay Pachaar Inverts LLM Agent Architecture with 'Harness' Design
AI engineer Akshay Pachaar outlined a novel 'harness' architecture for LLM agents that externalizes intelligence into memory, skills, and protocols. He is building a minimal, didactic open-source implementation of this design.
Claude Code Reverse-Engineered: 98.4% of Codebase is Operational Harness
A reverse-engineering analysis of Claude Code reveals only 1.6% of its codebase is AI decision logic, with the rest being operational infrastructure. This challenges current agent design paradigms by prioritizing a robust deterministic harness over complex model routing.
Agent Harness Debate: Anthropic vs. OpenAI vs. LangChain on Scaffolding
A central debate in agent engineering pits a 'thin harness' approach (Anthropic) against 'thick harness' designs (LangGraph). The infrastructure layer, not the model, is becoming the primary product differentiator.
Agent Harness Engineering: The 'OS' That Makes LLMs Useful
A clear analogy frames raw LLMs as CPUs needing an operating system. The agent harness—managing tools, memory, and execution—is what creates useful applications, as proven by LangChain's benchmark jump.
Stanford/MIT Paper: AI Performance Depends on 'Model Harnesses'
A new paper from Stanford and MIT introduces the concept of 'Model Harnesses,' arguing that the wrapper of prompts, tools, and infrastructure around a base model is a primary determinant of real-world AI performance.
Meta-Harness from Stanford/MIT Shows System Code Creates 6x AI Performance Gap
Stanford and MIT researchers show AI performance depends as much on the surrounding system code (the 'harness') as the model itself. Their Meta-Harness framework automatically improves this code, yielding significant gains in reasoning and classification tasks.
Harness Engineering for AI Agents: Building Production-Ready Systems That Don’t Break
A technical guide on 'Harness Engineering'—a systematic approach to building reliable, production-ready AI agents that move beyond impressive demos. This addresses the critical industry gap where most agent pilots fail to reach deployment.
MiniMax M2.7 AI Agent Rewrites Its Own Harness, Achieving 9 Gold Medals on MLE Bench Lite Without Retraining
MiniMax's M2.7 agent autonomously rewrites its own operational harness—skills, memory, and workflow rules—through a self-optimization loop. After 100+ internal rounds, it earned 9 gold medals on OpenAI's MLE Bench Lite without weight updates.
ChatGPT GPT-5.4 Pro's 'Thinking' Harness Shows Advanced Scientific Paper Comprehension, Including Figure Analysis
OpenAI's ChatGPT GPT-5.4 Pro, with its 'Thinking' harness, demonstrates advanced multimodal understanding of scientific papers, identifying key figures and extracting visual information beyond text parsing.
Meta-Harness Framework Automates AI Agent Engineering, Achieves 6x Performance Gap on Same Model
A new framework called Meta-Harness automates the optimization of AI agent harnesses—the system prompts, tools, and logic that wrap a model. By analyzing raw failure logs at scale, it improved text classification by 7.7 points while using 4x fewer tokens, demonstrating that harness engineering is a major leverage point as model capabilities converge.
Anthropic's 'Harness' Design: What It Means for Your Claude Code Workflows
Anthropic's new 'harness' architecture for long-running apps could enable Claude Code to manage more complex, persistent development tasks with greater stability.
Google DeepMind's AutoHarness: The AI Tool That Could Revolutionize How We Build Intelligent Systems
Google DeepMind's AutoHarness framework enables automatic testing and optimization of AI models without retraining, allowing developers to synthesize functional AI agents like coding assistants with unprecedented efficiency.
MIT's 'Agent Harness' Unleashes Proactive AI That Can Independently Navigate Complex Tasks
MIT researchers have developed a groundbreaking 'agent harness' system that enables AI agents to proactively plan and execute multi-step tasks with minimal human intervention. This represents a significant leap toward truly autonomous AI systems that can navigate complex, real-world scenarios independently.
Agent Harness Scaling: EFC Predicts Success at R2 0.99 vs 0.42
New research introduces Effective Feedback Compute (EFC), which predicts agent success at R2 0.99 vs 0.42 for raw tokens. Reallocating compute by EFC lifts success 3x at the same budget.