logoalt Hacker News

ctbellmar • today at 6:53 PM • 1 reply • view on HN

Similar experience here. The spirals on long running tasks are out of control at times with hours going by without a conclusion.


Replies

SOLAR_FIELDS • today at 6:55 PM

They (OpenAI models) are very tuned to be depth first and you can coach them all you want to try to be breadth first but as that context window fills up on those long running tasks they drift back to their first principles, which means obsessively testing and verifying a singular task rather than proceeding to the next task on the list

➕ show 1 reply