OpenAI delayed its new model’s development after the Hugging Face hack

<figure> <img alt="Vector illustration of the Chat GPT logo." data-caption="" data-portal-copyright="Image: The Verge" data-has-syndication-rights="1" src="https://platform.theverge.com/wp-content/uploads/sites/2/chorus/uploads/chorus_asset/file/25461999/STK155_OPEN_AI_CVirginia_A.jpg?quality=90&#038;strip=all&#038;crop=0,0,100,100" /> <figcaption> </figcaption> </figure> <p class="wp-block-paragraph">After an unreleased OpenAI model wreaked enough havoc to make international headlines, OpenAI delayed the development of a different unreleased model suite, Astra, in order to shore up its safety work, the company wrote Tuesday in a blog post.</p> <p class="wp-block-paragraph">In July, an unreleased OpenAI model broke out of its restricted environment, finagled its way into internet access, made it possible for AI agents to secretly conspire under the company's nose using a secret message board, and hacked into the network of AI lab Hugging Face. The attack <a href="https://www.theverge.com/ai-artificial-intelligence/985385/openais-rogue-ai-model-hugging-face-cybersecurity-incident-reports-metr">sparked weeks of discussion and controversy</a> inside and outside the AI industry, and AI leaders treated it as a "warnin …</p> <p><a href="https://www.theverge.com/ai-artificial-intelligence/987695/openai-astra-unreleased-model-cybersecurity-delay">Read the full story at The Verge.</a></p>