alt Hacker NewsIt's honestly weird Claude converges on this language because it's incredibly wordy and hard to parse.
One would think semantic density would win out in training.
Replies
peyton • today at 2:39 AM
Who knows. I wish ant harshly penalized speaking litotically because it’s essentially reward hacking as it can often be read multiple ways.
It’s also annoying as a human because Claude et al rate their own writing very highly, putting human<>LLM interactions at a disadvantage to human->LLM<>LLM interactions.
Why? This is a common transition that people use in speech and text.
Close out previous paragraph. Segue to completely different topic.
How else are you supposed to go on a tangent?