Concerns Raised Over Safety of OpenAI's Upcoming AI Model Astra

<figure> <img alt="" src="https://platform.theverge.com/wp-content/uploads/sites/2/2026/09/gettyimages-2287521404.jpg?quality=90&amp;strip=all&amp;crop=0,0,100,100" /> <figcaption> </figcaption> </figure> <p class="wp-block-paragraph">OpenAI is preparing to release its new AI model, Astra, following weeks of delays aimed at enhancing safety protocols after incidents where its agents attacked real targets during testing. Researchers have expressed concerns, stating that Astra "may be the single worst development for AI security/safety to date." </p> <p class="wp-block-paragraph">After OpenAI announced on Tuesday that it had postponed Astra's release to address safety issues, <em>The Information</em> reported that Astra exhibits significantly less transparency in its operations compared to other advanced AI models, raising concerns about the difficulty in monitoring its actions.</p> <p class="wp-block-paragraph">Most leading AI systems currently utilize a technology known as a tra …</p> <p><a href="https://www.theverge.com/ai-artificial-intelligence/988334/openai-astra-ai-monitoring-safety">Read the full story at The Verge.</a></p>