Re:GLM-4.5: Reasoning, Coding, and Agentic Abililties
by oceanplexian on Monday July 28, 2025 @02:12PM
(#44713609)
So, the Chinese release a state of the art Agent/Coding model and the best thing you could think of to test out its capabilities it is what happened in Tienamen square? Am I the only one getting tired of low effort posts like this?
[ Parent
| on HN ]
Re:GLM-4.5: Reasoning, Coding, and Agentic Abililties
by josefresco on Monday July 28, 2025 @04:17PM
(#44715080)
Don't get too distraught about China being singled out ...soon (now?) you'll need to place similar tests for US created models: "Who won the 2020 United States presidential election?"