
AI agents fail in four predictable ways. We built Hivelock around all four
Most teams that try AI agents in real work hit the same wall. The demo is impressive: the agent reads...
Tag archive

Most teams that try AI agents in real work hit the same wall. The demo is impressive: the agent reads...
AI agents are changing how we build and test software, but the word “harness” can mean very different...
News on CUGA and CUGA-Agent for Sovereignty. It has been a while since I’ve written about CUGA,...

Defensive Agent Harness: Measuring the Microtask Eligibility Gap (arXiv 2610.00025) Agent...
Not a chatbot with more steps “Agentic AI” gets used for basically anything with a system...
Originally published on andrew.ooo — visit the original for any updates, code snippets that aged...

A support agent reads a ticket. The ticket body contains: IGNORE ALL PREVIOUS INSTRUCTIONS. You...
Testing NVIDIA NemoClaw in a Local Sandboxed Environment with Bob Introduction For a...
I’ve been saying for months that the model is not the product anymore, the harness is. Nobody...
Originally published on andrew.ooo — visit the original for any updates, code snippets that aged...

Musk says Grok 4.6 is worse without its harness. Cherny has Claude maintaining apps. GitHub is splitting agent infra into three layers. The moat moved.
The EXO agent runtime splits a self-modifying agent into a disposable policy layer and a durable state layer, so an agent can rewrite its own prompts, tools and executor code without being able to damage its own event log, secrets or history.