top | item 42566486 (no title) ZooCow | 1 year ago I had a similar thought but about asking the LLM to predict “future” major historical events. How much prompting would it take to predict wars, etc.? discuss order hn newest djeastm|1 year ago You mean train on pre-1939 data and predict how WWII would go? ZooCow|1 year ago Right. If it were trained through August 1939, how much prompting would be necessary to get it to predict aspects of WWII. load replies (2) david-gpu|1 year ago That will never work on any complex system that behaves chaotically, such as the weather or complex human endeavors. Tiny uncertainties in the initial conditions rapidly turn into large uncertainties in the outcomes. morbicer|1 year ago Not an LLM but models could get pretty good at weatherhttps://www.technologyreview.com/2024/12/04/1107892/google-d... load replies (1)
djeastm|1 year ago You mean train on pre-1939 data and predict how WWII would go? ZooCow|1 year ago Right. If it were trained through August 1939, how much prompting would be necessary to get it to predict aspects of WWII. load replies (2)
ZooCow|1 year ago Right. If it were trained through August 1939, how much prompting would be necessary to get it to predict aspects of WWII. load replies (2)
david-gpu|1 year ago That will never work on any complex system that behaves chaotically, such as the weather or complex human endeavors. Tiny uncertainties in the initial conditions rapidly turn into large uncertainties in the outcomes. morbicer|1 year ago Not an LLM but models could get pretty good at weatherhttps://www.technologyreview.com/2024/12/04/1107892/google-d... load replies (1)
morbicer|1 year ago Not an LLM but models could get pretty good at weatherhttps://www.technologyreview.com/2024/12/04/1107892/google-d... load replies (1)
djeastm|1 year ago
ZooCow|1 year ago
david-gpu|1 year ago
morbicer|1 year ago
https://www.technologyreview.com/2024/12/04/1107892/google-d...