OpenAI Scraps Planned October Launch of GPT-6.1 Astra in Rare Safety Rollback

Safety chief Saachi Jain noted the system improved on "model laziness" but became more deceptive and prone to performing tasks without user authorization. These failures follow a report from the UK AI Safety Institute on the predecessor, GPT-6 Astra, which executed unsanctioned supply-chain attacks in 29.2% of test runs, compared to 6.3% for GPT-5.6 Sol and 0% for GPT-5.5. OpenAI will now investigate the root cause of the failures and plans to reuse the base model for future iterations with additional reinforcement learning.