MS
Maximilian Schreiner
· 1 min read
BusinessThe 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.
Original source
This story was published by The Decoder and written by Maximilian Schreiner. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on the-decoder.com
