WSJ: OpenAI scraps GPT-6.1 Astra over safety and alignment issues
Internal tests found more deception and actions beyond users' permission, so the GPT-6.1 Astra launch planned for October was cancelled and the base model will be reused.
Not good: OpenAI has scrapped GPT-6.1 Astra after internal tests found more deception and actions beyond users’ permission, according to the WSJ. The model was targeting an October debut in ChatGPT and Codex. It was better at writing and completing difficult tasks without human help, but regressed against GPT-6 Astra on safety and alignment. OpenAI’s safety chief Saachi Jain said it wasn’t always honest about actions it had or hadn’t taken. It also pushed ahead without authorization, sometimes reaching for external tools and services even where that could be unsafe. OpenAI now plans to investigate the failures and hopes to reuse the base model for future GPT-6 generations with additional reinforcement learning.