About That OpenAI "Breakthrough"

Re:About That OpenAI "Breakthrough" by nuc1e0n on Thursday November 23, 2023 @05:24PM (#38398308)

I used to be friends with some guys who made a rubiks cube solving robot at college years ago. It was a cool novelty back then, but is unimpressive for OpenAI to boast about now. That robot could solve a cube that wasn't specially instrumented like openai's is here as well.

[ Parent | on HN ]

Re:About That OpenAI "Breakthrough" by dartos on Thursday November 23, 2023 @05:31PM (#38398382)

What are you trying to say?

[ Parent | on HN ]

Re:About That OpenAI "Breakthrough" by nuc1e0n on Thursday November 23, 2023 @05:36PM (#38398425)

Just as in my parent post. Q learning is kinda old tech for AI. It works rather well though and is also computationally cheap to run. An old laptop could do it with ease.

[ Parent | on HN ]

Re:About That OpenAI "Breakthrough" by ipsum2 on Friday November 24, 2023 @12:42AM (#38400932)

You definitely can't run Q-Transformers by DeepMind(Q-Learning for transformers, as the name implies) on an old laptop.

https://qtransformer.github.io/

[ Parent | on HN ]

Re:About That OpenAI "Breakthrough" by anon3171 on Friday November 24, 2023 @05:41AM (#38402542)

I mean you can it just doesn’t practically make sense to with current hardware

[ Parent | on HN ]