News for hackers. Stuff that matters.
Re:Google SIMA by mike_hearn on Wednesday March 13, 2024 @04:56PM (#39697404)
You can control LLMs to any arbitrary degree of specificity by a mix of retraining and changing the decoding strategies. They can be as predictable as needed, I think the bigger issue is more like how do you write stories when the possibilities get so much larger.
Re:Google SIMA by summerlight on Wednesday March 13, 2024 @05:58PM (#39698090)
Yes, less predictability is a part of the problems from the unconstrained search space. I think technically there is a room for improvement, but this usually needs ML expertise, which most of game designers and engineers do not have at this moment.