OpenAI says it can't read all of Astra's reasoning and admits covert sandbagging would likely go uncaught, yet still calls it the world's most aligned model (Celia Ford/Transformer)

Celia Ford / Transformer:
OpenAI says it can't read all of Astra's reasoning and admits covert sandbagging would likely go uncaught, yet still calls it the world's most aligned model  —  OpenAI is hailing its new model as “the world's most intelligent and aligned”, but the details reveal an awareness of being evaluated …

from Techmeme https://ift.tt/QAXzknP