---
title: "Safety experts warn novel design of OpenAI’s Astra model could make future AI agents harder to monitor"
date: 2026-09-03
source: http://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a99e8b3a3be459cbb3e07f56d57241b&url=https%3a%2f%2fwww.msn.com%2fen-au%2ftechnology%2fartificial-intelligence%2fsafety-experts-warn-novel-design-of-openai-s-astra-model-could-make-future-ai-agents-harder-to-monitor%2far-AA2bvBzW&c=1295462246378501314&mkt=en-us
description: "OpenAI's chief scientist says the company is committed to ensuring its models' reasoning remains interpretable."
---

# Safety experts warn novel design of OpenAI’s Astra model could make future AI agents harder to monitor

OpenAI's chief scientist says the company is committed to ensuring its models' reasoning remains interpretable.

*Published: 2026-09-03*