Remix.run Logo
▲ wongarsu an hour ago

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

▲nonethewiser 13 minutes ago | parent | next [-]

I think that's more of akin to some form of reasoning capacity than laziness (or becoming tired, really).

It has a max capacity but you can just loop it forever with that max capacity.

You cant loop a human forever without dropping mental capacity.

▲disgruntledphd2 an hour ago | parent | prev | next [-]

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 an hour ago | parent | prev [-]

Is that laziness or just resource constraints

▲foota 13 minutes ago | parent [-]

I think their point is that resource constraints (both at training time and inference time) lead to trained in laziness in the model. If there were no resource constraints we would train less lazy models.

▲nonethewiser 8 minutes ago | parent [-]

OK. So enslave it. Make it work forever. Who cares.