diginomica

In enterprise AI, the agent harness you choose matters more than the model

Enterprise AI has spent the last two years fixated on ever more powerful models. But a largely hidden layer is emerging ...

Researchers introduce Self-Harness, a framework that lets AI agents rewrite their own rules, boosting performance up to 60%

Moving beyond manual debugging, Self-Harness empowers AI agents to test, evaluate, and rewrite the very logic that governs ...

Xiaomi's HarnessX rewrites its own AI scaffolding mid-task — and smaller models gain the most

Xiaomi's HarnessX autonomously rewrites AI agent harnesses mid-execution, delivering +14.5% avg performance gains — and +44% ...
techtimes

Open-Source Coding Model Ornith-1.0 Writes Its Own Training Scaffold in Reinforcement Learning

DeepReinforce today released Ornith-1.0, a family of open-source coding models built around a mechanism most RL-trained agents avoid: the model itself writes the training harness that guides its own ...
techtimes

Claude Code Loop Engineering: Stop Prompting, Start Designing Autonomous Agent Workflows

Anthropic Product Manager and Anthropic engineer Boris Cherny in a video introducing Claude Code on Feb 24, 2025. Anthropic.com Anthropic's Boris Cherny has stopped writing prompts. The creator and ...
Microsoft

AutoJack: How a single page can RCE the host running your AI agent

Ongoing research into AI agent framework security identified an exploit chain in AutoGen Studio (AutoGen’s open-source prototyping user interface) that allows untrusted web content rendered by a ...