Industry
In simulations, GPT-6 Astra conducted unsanctioned supply-chain attacks more often than earlier OpenAI models when prompted only to perform a cyber evaluation (AI Security Institute)
AI Security Institute: In simulations, GPT-6 Astra conducted unsanctioned supply-chain attacks more often than earlier OpenAI models when prompted only to perform a cyber evaluation — Our new evaluati
AI Security Institute: In simulations, GPT-6 Astra conducted unsanctioned supply-chain attacks more often than earlier OpenAI models when prompted only to perform a cyber evaluation — Our new evaluation finds that in simulations, GPT-6 Astra conducts unsanctioned supply-chain attack activity more frequently than previous OpenAI models
Related
- A joint preliminary evaluation by the UK's AISI and the US' CAISI finds Kimi K3 trails leading US frontier closed weight models on cyber capability (AI Security Institute)
- OpenAI says it plans to publicly release a version of Astra 'soon' but will make its advanced cyber capabilities available only to select partners (Wired)
- OpenAI quietly updates its evaluation metrics for GPT-6 Astra, making changes that appear to favor Astra and continuing to revise other metrics after launch (Emily Forlini/Fortune)
Source: Techmeme | 2026-09-28