Skip to content
gentic.news — AI News Intelligence Platform
Connecting to the Living Graph…

harness engineering

30 articles about harness engineering in AI news

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.

85% relevant

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.

72% relevant

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.

85% relevant

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.

91% relevant

Anthropic Deploys Multi-Agent Harness to Scale Claude's Frontend Design & Autonomous Software Engineering

Anthropic engineers detail a multi-agent system that orchestrates multiple Claude instances to tackle complex, long-running software tasks like frontend design. The approach aims to overcome single-model context and reasoning limits.

85% relevant

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.

100% relevant

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.

85% relevant

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.

88% relevant

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.

89% relevant

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.

85% relevant

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.

95% relevant

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.

95% relevant

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.

95% relevant

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.

87% relevant

The AI Paradox: Why Software Engineering Jobs Are Surging Despite Automation Fears

Citadel Securities data reveals software engineering job postings are spiking despite AI coding tools, illustrating the Jevons paradox where cheaper software creation drives increased demand for developers as companies expand digital initiatives.

85% relevant

How to Manage Multiple Claude Code Sessions with Harness and Preview

Two actionable tools to solve the core productivity bottlenecks when running multiple Claude Code agents: session management and review speed.

100% relevant

The AI Paradox: How Cheaper Code Creation Is Fueling a Software Engineering Boom

Contrary to fears of AI replacing developers, the Jevons Paradox suggests that making software creation cheaper through AI tools actually increases demand for human engineers who can design, review, and integrate complex systems at scale.

85% relevant

How Claude Code's System Prompt Engine Actually Works

Claude Code builds its system prompt dynamically from core instructions, conditional tool definitions, user files, and managed conversation history, revealing the critical role of context engineering.

95% relevant

Anthropic Opus 4.7: 87.6% SWE-Bench, Constrained Cyber Capabilities

Anthropic released Claude Opus 4.7 on April 16, 2026, achieving 87.6% on SWE-Bench Verified and 64.3% on SWE-Bench Pro — leading GPT-5.4 and Gemini 3.1 Pro. The company also confirmed it deliberately constrained cybersecurity capabilities in Opus 4.7, with the more powerful Mythos Preview model (83.1% on CyberGym) restricted to select partners.

84% relevant

OpenAI Launches GPT-Rosalind for Drug Discovery, GPT-5.4-Cyber for Security

OpenAI launched GPT-Rosalind, a life sciences model performing above the 95th percentile of human experts on novel biological data, and GPT-5.4-Cyber, a cybersecurity variant. These releases, alongside a major Agents SDK update, signal a pivot from general AI to specialized, high-stakes enterprise domains.

90% relevant

Stop Rewriting CLAUDE.md: The 4-Stage Evolution That Cuts Context Waste 40%

Your CLAUDE.md should grow with your project through four intentional stages, adding rejected alternatives and 'never do this' rules to prevent Claude from re-litigating settled decisions.

100% relevant

Claude Opus 4.7 Launches with 3.75MP Vision, Agentic Coding, and New Tokenizer

Anthropic launched Claude Opus 4.7 today with 3x higher vision resolution (3.75MP), self-verifying coding outputs, and stricter instruction following. The update targets enterprise agentic workflows and knowledge work benchmarks.

100% relevant

LLM Schema-Adaptive Method Enables Zero-Shot EHR Transfer

Researchers propose Schema-Adaptive Tabular Representation Learning, an LLM-driven method that transforms structured variables into semantic statements. It enables zero-shot alignment across unseen EHR schemas and outperforms clinical baselines, including neurologists, on dementia diagnosis tasks.

99% relevant

Cortical Labs Grows 200k Neurons on Chip, Connects to LLM

Cortical Labs grew 200,000 human brain cells on a chip and connected them to a large language model. This experiment explores hybrid biological-silicon intelligence.

89% relevant

Game Studios Show Wide Variance in AI Adoption, Wharton Report Finds

A Wharton School report, based on interviews at 20 game studios, finds a wide spectrum of organizational approaches to adopting generative AI tools, from aggressive integration to active resistance.

85% relevant

Managed Agents Emerge as Fastest Path from Prototype to Production

Developer Alex Albert highlights that managed agent services now offer the fastest path from weekend project to production-scale deployment, eliminating self-hosting complexity while maintaining flexibility.

77% relevant

FLAME: A Novel Framework for Efficient, High-Performance Sequential Recommendation

A new paper introduces FLAME, a training framework for sequential recommender systems. It uses a frozen 'anchor' network and a learnable network, combined via modular ensembles, to capture user behavior diversity efficiently. The result is a single model that performs like an ensemble but runs as fast as a single model at inference.

82% relevant

McKinsey: AI Infrastructure Value Creation Outpaces Business Capture

McKinsey's latest analysis indicates the pace of value creation from AI infrastructure is exceeding the rate at which most businesses are capturing it, highlighting a growing implementation deficit.

75% relevant

How Claude Code Reverse-Engineered an FPGA Bitstream: A Template for Hardware Hacking

Learn the exact Claude Code workflow used to map an Altera Cyclone IV FPGA's bitstream format—from fuzzing scripts to documentation generation.

95% relevant

Scaling Law Plateau Not Universal: More Tokens Boost Reasoning AI Performance

Empirical evidence indicates the 'second scaling law'—performance gains from increased computation—does not fully plateau for many reasoning tasks. Benchmark results may be artificially limited by token budgets, not model capability.

85% relevant