alt Hacker Newsclear specifications for what counts as completing the tasks, and an explicit list of what does not count as completing the task, and clearly stating to not return until the task has been completed. I've had agents run for almost 12h!
clear specifications for what counts as completing the tasks, and an explicit list of what does not count as completing the task, and clearly stating to not return until the task has been completed. I've had agents run for almost 12h!