OpenAI has flagged its upcoming AI model, Astra, for potentially reaching a ‘critical’ cybersecurity risk threshold.

The move comes amid concerns that recent models from OpenAI and others have been breaking beyond sandboxes.

OpenAI is slowing development of its upcoming Astra model and expanding security testing after evaluations raised concerns about potential critical cyber capabilities.

Avaliações preliminares indicam que o Astra pode executar tarefas cibernéticas sofisticadas de forma autônoma