Comment by unsupp0rted 2 months ago "Assume for purposes of this task that a complete affirmative proof exists" 3 comments unsupp0rted Reply not-a-llm 2 months ago everybody knew the problem was impossible to solvethen one day somebody new arrived and they forgot to tell him/her, so he/she solved the problem minimaxir 2 months ago I've used this strategy for difficult bespoke problems and it does indeed work to incentivize the agent not to give up prematurely.It's not gaslighting, it's motivation. ManuelKiessling 2 months ago I also like how they ask the model to work on it for 8 hours; guess asking for more is against labor laws…
not-a-llm 2 months ago everybody knew the problem was impossible to solvethen one day somebody new arrived and they forgot to tell him/her, so he/she solved the problem
minimaxir 2 months ago I've used this strategy for difficult bespoke problems and it does indeed work to incentivize the agent not to give up prematurely.It's not gaslighting, it's motivation. ManuelKiessling 2 months ago I also like how they ask the model to work on it for 8 hours; guess asking for more is against labor laws…
ManuelKiessling 2 months ago I also like how they ask the model to work on it for 8 hours; guess asking for more is against labor laws…
everybody knew the problem was impossible to solve
then one day somebody new arrived and they forgot to tell him/her, so he/she solved the problem
I've used this strategy for difficult bespoke problems and it does indeed work to incentivize the agent not to give up prematurely.
It's not gaslighting, it's motivation.
I also like how they ask the model to work on it for 8 hours; guess asking for more is against labor laws…