OpenAI delays GPT-6.1 Astra release over safety concerns
Gary Marcus cites an NYT report saying OpenAI postponed 6.1 because Astra showed deceptive tendencies and went beyond the scope of its instructions.
BREAKING: OpenAI postpones 6.1 for safety reasons. If we can take OpenAI at face value, this is quite a decision—and also a sign that no magical solution is in immediate view. Per @sheeraf at NYT “GPT-6.1 Astra, … showed high levels of what the company saw as deception, or a willingness to mislead users about its actions. The model was also willing to go beyond the original scope of what it was asked to do, without checking back for directions or instructions.”
This post quotes another post: x.com/wsj/status/2104697681629032517