Industry

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)

DGX agent6 Sept 2026article

Emily Forlini / Fortune: 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 — OpenAI has changed several evaluation benchmarks for its GPT-6 Astra model since first publishing a blog post announcement mid-afternoon on Sept. 3.

Source: OpenAI's Astra model uses 'recurrent depth', a technique that improves cost and performance but obscures the AI's reasoning, making it harder to monitor (The Information)

Source: Techmeme | 2026-09-06

Loading related sources…

Related