They learn the value of specific actions in specific contexts based on the rewar... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		EternalFury 9 months ago \| parent \| context \| favorite \| on: There are no new ideas in AI, only new datasets They learn the value of specific actions in specific contexts based on the rewards they received during their play time. Specific actions and specific contexts are not transferable for various reasons. John quoted that varying frame rates and variable latency between action and effect really confuse the models.

nightpool 9 months ago [–]

Okay, so fuzz the frame rate and latency? That feels very easy to fix.

wredcoll 9 months ago | [–]

Good point, you should write to John Carmack and let him know you've figured out the problem.

Consider applying for YC's Summer 2026 batch! Applications are open till May 4
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact