Comment by hodgehog11
7 hours ago
I also believe this. Post-training LLMs with vague metrics can only be achieved with RLHF, which is not impossible, but extremely costly and difficult. Instead, companies will opt for RLVR, focusing on math and programming tasks. This pushes objectives away from writing quality; often far away. That is why older models, in my view, actually read better than newer ones. It's by design.
You can brute force it by making it try random stuff then judge itself on it. You don't have to always use an LLM's output. Sometimes you can use that plus other things to add flavor. An LLM is actually really good at judging if something is good or bad. It just has a really hard time coming up with new things. But if you had unlimited compute you can throw in some rng and whimsy and get something resembling what humans do.