alt Hacker NewsWhile the caveman stuff is obviously not serious, there is a lot of legit research in this area.
Which means yes, you can actually influence this quite a bit. Read the paper “Compressed Chain of Thought” for example, it shows it’s really easy to make significant reductions in reasoning tokens without affecting output quality.
There is not too much research into this (about 5 papers in total), but with that it’s possible to reduce output tokens by about 60%. Given that output is an incredibly significant part of the total costs, this is important.
Replies
Some labs do it internally because RLVR is very token-expensive. But it degrades CoT readability even more than normal RL pressure does.
It isn't free either - by default, models learn to offload some of their internal computation into the "filler" tokens. So reducing raw token count always cuts into reasoning capacity somewhat. Getting closer to "compute optimal" while reducing token use isn't an easy task.
Yeah you could easily imagine stenography like inputs and outputs for rapid iteration loops. It's also true that in social media people already want faster-to-read snippets that drop grammar so the desire for density is already there for human authors/readers.
Who would suspect that the companies selling 'tokens' would (unintentionally) train their models to prefer longer answers, reaping a HIGHER ROI (the thing a publicly traded company is legally required to pursue: good thing these are all still private...)... because it's not like private companies want to make money...