Comment Comment by minimaxir > just repeatedly saying "keep going" to ChatGPTFor posterity, this indeed works for most problems where an agent might give up. LLMs don't inherently know something is impossible.The phrase I tend to use in my harder prompts to automate this with a sane loop breaker:> **REPEAT THIS PROCESS UNTIL CONVERGENCE AND YOU ARE OUT OF OPTIMIZATION IDEAS.** You have permission to keep iterating. parent minimaxir 3 months ago
For posterity, this indeed works for most problems where an agent might give up. LLMs don't inherently know something is impossible.
The phrase I tend to use in my harder prompts to automate this with a sane loop breaker:
> **REPEAT THIS PROCESS UNTIL CONVERGENCE AND YOU ARE OUT OF OPTIMIZATION IDEAS.** You have permission to keep iterating.