News for hackers. Stuff that matters.
Re:Prof. Software Developers Don't Vibe, They Control: AI Ag... by HarHarVeryFunny on Tuesday December 30, 2025 @10:54PM (#46441092)
The entire history of RL-trained "reasoning models" from o1 to DeepSeek_R1 is basically just a year old!

There are no comments on this comment yet.