Eji
@ejiwarp
Sat, Nov 2, 2024 6:21 PM
Sat, Nov 2, 2024 7:54 PM
LLMs don't do formal reasoning | Hacker News
GSM-Symbolic: Understanding the Limitations of Mathe...
Functional Benchmarks for Robust Evaluation of Reaso...
Apple DROPS AI BOMBSHELL: LLMS CANNOT Reason
苹果发文质疑：大语言模型根本无法进行逻辑推理-36氪
這好像很直觀
載入新的回覆