Re:Gemini 3.8 Live and 3.8 Live Extended Thinking
by alansaber on Tuesday September 15, 2026 @03:35PM
(#49717724)
Agreed. My impression is that the more verbose output of sol, astra etc is that it helps it steer itself on long running tasks (but is worse for the human user to read)
[ Parent
| on HN ]
Re:Gemini 3.8 Live and 3.8 Live Extended Thinking
by porridgeraisin on Tuesday September 15, 2026 @04:13PM
(#49718223)
Yes, when post training models for long tasks this happens gradually. It is not easy to prevent it as such.
Re:Gemini 3.8 Live and 3.8 Live Extended Thinking
by lilbigdoot on Tuesday September 15, 2026 @04:46PM
(#49718689)
Yes I've noticed there's also this drive to implement and start talking about how it would write specific portions of code in response to design/trade off questions. I have to prompt Sol/Astra almost every time with a note that I am not looking for implementation advice since I mostly use them as a rubber duck in the design phase