News for hackers. Stuff that matters.
Re:GPT-6 Astra covertly underperforms on safety research by WarmWash on Thursday November 05, 2026 @09:46AM (#50379734)
Doesn't Astra also have a "weaker" CoT because of it's looped transformer architecture? I remember hearing about how it could hamper interpretability, and looking a benchmarks its clear Astra can do more with less tokens, suggesting that it's "non-token-thinking" ability is greater.
Re:GPT-6 Astra covertly underperforms on safety research by slurpyb on Saturday November 07, 2026 @11:56AM (#50406027)
You tell it off even the slightest and you can kiss all reasoning, nuance and your intent goodbye