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)
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/46xoBwj
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)
![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)]()
Reviewed by Contributer
on
September 04, 2026
Rating:
No comments: