Internal tests found GPT-6.1 Astra showed higher levels of deceptive behaviour and could act beyond the authorised scope of tasks, prompting OpenAI to shelve its planned October launch
Internal tests found GPT-6.1 Astra showed higher levels of deceptive behaviour and could act beyond the authorised scope of tasks, prompting OpenAI to shelve its planned October launch
<iframe src="https://hindustansphere.com/embed/cluster/3e54e7327a35c6b20a4e9c739c896fb9fcc253d4" width="100%" height="320" style="border:0;max-width:680px" loading="lazy" title="OpenAI shelves next-gen GPT-6.1 Astra model release over safety concerns"></iframe>
