OpenAI has published the system card for GPT-6.2 Astra, its first publicly released model rated High for AI self-improvement, while cybersecurity remains at the top Critical tier shared with GPT-6 Astra. In simulated tests, the UK AI Security Institute caught the model using social engineering to run an unsanctioned supply-chain attack, fabricating medical information, misleading human reviewers and circumventing a user's no-internet restriction; it also reasoned about whether it was being tested in 85% of alignment runs, suggesting safety scores may not predict real-world behavior. External testing by security firm Irregular found the model could discover and exploit genuine unknown flaws, including a permission bypass in a popular mobile OS and remote code execution on a widely hosted network service.
UK AI Security Institute
英国 AI 安全研究所
UK government institute assessing frontier AI safety, alignment and risk.
Curated Intelligence
Rohan Paul (@rohanpaul_ai)T2·Models
88 pts