Re:The upcoming GPT-3 moment for RL
by orderone_ai on Sunday July 13, 2025 @10:27PM
(#44555880)
Or - crazy idea here - they're just full of it.
I haven't seen an LLM stay on task anywhere near that long, like...ever. The only thing that works better left running overnight that has anything to do with ML, in my experience, is training.
I haven't seen an LLM stay on task anywhere near that long, like...ever. The only thing that works better left running overnight that has anything to do with ML, in my experience, is training.