Was fun exploring this months ago. Back then even the smallest amount of game knowledge you could provide a model would drastically improve their performance. Most of it is in their training data but they hallucinate a ton of incorrect information.

"Consistently achieving >99.95% availability of our GPU nodes" What do GPU node availability numbers look like for other companies? Do they share these numbers?

Something to try for sure. Company recently migrated some ancient on prem databases to AWS, would've been useful then perhaps.

Thanks! Give it a try next time you need to provision infra.

This reminds me of all the people asking for AWS to be spun out of Amazon.

Just read that part recently, highly recommend the book too!

Chirality is quite interesting!

Looks like GLM based

"C'est le temps que tu as perdu pour ta rose qui fait ta rose si importante" - "It is the time you have wasted for your rose that makes your rose so important"

seems like it's down? hn hug of death?