#FormalReasoning

Norobiik @Norobiik@noc.socialNorobiik@noc.social
2024-10-15

The results of this new GSM-Symbolic paper aren't completely new in the world of #AI research. Other recent papers have similarly suggested that #LLMs don't actually perform #FormalReasoning and instead mimic it with probabilistic #PatternMatching of the closest similar data seen in their vast training sets. #GenAI

#Apple study exposes deep cracks in LLMs’ “reasoning” capabilities
arstechnica.com/ai/2024/10/llm

Client Info

Server: https://mastodon.social
Version: 2025.07
Repository: https://github.com/cyevgeniy/lmst