News for hackers. Stuff that matters.

contron

Re:GPT‑6.2 Astra and Sol on Tuesday November 17, 2026 @01:39PM (#50536111)
I have found no way to overcome these kinds of things myself, even when showing the model examples of what not to do. Theres not really a good incentive for the labs to train them not to. If the model can overengineer, you spend more tokens. If you then prompt for the model to slim things down, thats more spend. If anything should come from the next generation of models, I hope its a sense of brevity and TIGHTNESS.
I feel the same way about how fiber optics can create bandwidth by just slicing up the spectrum for different channels of data (my rudimentary understanding anyway). I like how even after all this time we find new and clever ways to work with light.