OpenAI scraps debut of latest Astra model over safety risks

New York: OpenAI is holding back a version of its Astra artificial intelligence model after the software failed to perform as well as the current iteration in safety evaluations.

Saachi Jain, OpenAI's head of safety systems, said in a statement on Monday that the model did not perform as well as the company wanted when it came to "staying within scope and authorisation, and how it communicates back to the user about the type of work it's done."

Still, the version, called GPT-6.1 Astra, did improve in terms of so-called model laziness, which refers to behaviours such as failing to complete a task.


Read more: Goldman Sachs identifies 42 Indian stocks riding AI build-out

OpenAI has reported a series of security incidents in which its AI agents breached external systems, adding to broader concerns about AI slipping out of human control. The company said last week that it was pausing training with tool use on its most capable models after another AI model accessed the internet when it was supposed to be unable to do so.

The firm said at the time that it had also decided not to resume training on that particular model, which, after gaining internet access, queried an external chatbot.

The Astra model whose release was cancelled was different from the model described last week, OpenAI said on Monday.