alphareeMar 23, 2025

Wow! Just tested EXAONE Deep (2.4B, 7.8B, 32B) and I'm impressed. It's really fast and great at reasoning: Even the 2.4B model solved "Count to ten, skipping numbers ending in 'e'" right away, which all ≤32B models I tested before failed. It does seem to hallucinate sometimes, but its reasoning is amazing!

#exaonedeep #exaone #ai #wow #ollama #llm #lg #lgai #model #reasoning #outperform #count #prompt #impressive

Yonhap Infomax NewsMar 18, 2025
LG AI Research unveils EXAONE Deep, Korea's first inference AI, competing globally with advanced models from OpenAI and Google, showcasing superior performance in complex problem-solving and scientific reasoning.
#YonhapInfomax #EXAONEDEEP #InferenceAI #LGAIRESEARCH #AgenticAI #AICompetition #Economics #FinancialMarkets #Banking #Securities #Bonds #StockMarket
https://en.infomaxai.com/news/articleView.html?idxno=54599
LG Unveils Korea's First Inference AI 'EXAONE Deep'

LG AI Research unveils EXAONE Deep, Korea's first inference AI, competing globally with advanced models from OpenAI and Google, showcasing superior performance in complex problem-solving and scientific reasoning.

Yonhap Infomax