logoalt Hacker News

wongarsu • today at 6:09 PM • 2 replies • view on HN

LLMs absolutely suffer from lazyness. Both reinforcement- training environments and benchmarks have token limits, which makes giving 100% on every subtask disadvantageous

They are less lazy than humans though


Replies

disgruntledphd2 • today at 6:30 PM

They are differently lazy from humans. They'll happily bang their heads against a wall to make something work, but they'll almost never step back to consider a different approach.

jtmarl1n • today at 6:26 PM

Is that laziness or just resource constraints