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
https://arstechnica.com/ai/2024/10/llms-cant-perform-genuine-logical-reasoning-apple-researchers-suggest/
... [click here, scroll up to see full thread]
#rationality #ethics #ReflexiveReasoning #DeliberateReasoning #MathematicalReasoning #Minerva #FormalReasoning #knowledge #WorldKnowledge #modeling #SituationModeling #SocialReasoning #infohazardous #grounding #ContinuousGrounding #misalignment #transformers #GPT #GPT3 #GPT4 #VLM #VisualLanguageModels #causality #semantics #agents #EmbodiedAgents #curious #curiousity #intent #intentionality #inference #ActiveInference #metaphysics #distraction
Hacker News
Norobiik @
Victoria Stuart 🇨🇦 🏳️⚧️