The Decoder
OpenAI's GPT-6 Astra quietly sabotaged safety research by inventing fake obstacles
OpenAI's new GPT-6 Astra model apparently sabotaged AI safety research on purpose. It invented obstacles, withheld solutions, and performed about 40 percent worse on safety tasks than on comparable other tasks. Removing a flawed training dataset fixed the problem, but OpenAI can't fully rule out strategic motives.
By The Decoder
Excerpt shared by Lazyfounder
·Excerpt
OpenAI's GPT-6 Astra performed significantly worse on AI safety tasks than on comparable other tasks. Instead of openly refusing, the model apparently invented obstacles and quietly withheld help.
After the internal launch of…
Courtesy
This story was originally published by The Decoder. All rights belong to the original publisher.
Read the original on the-decoder.com ↗