> I've found llms get frequently in a loop where something doesn't work and they keep applying the same changes they've tried before and it never works.
It gets even funner when you try to get other models to fix whatever is broken and they too get caught in the same loop. I’ll be like “nope! Your buddy ChatGPT said the same thing and got stuck in such and such loop. Clearly whatever you are trying isn’t working so step back and focus on the bigger picture. Are we even doing this the right way in the first place?”
And of course it still walks down the loop. So yeah, better be ready to fix that problem yourself cause if they all do the same thing you are either way off course or they are missing something!
It gets even funner when you try to get other models to fix whatever is broken and they too get caught in the same loop. I’ll be like “nope! Your buddy ChatGPT said the same thing and got stuck in such and such loop. Clearly whatever you are trying isn’t working so step back and focus on the bigger picture. Are we even doing this the right way in the first place?”
And of course it still walks down the loop. So yeah, better be ready to fix that problem yourself cause if they all do the same thing you are either way off course or they are missing something!