Frontier Models vs. Mathletes: The Great IMO Showdown
·125 words·1 min
Blog
LLM Judges Prefer Fluff—Just Like Humans!
·47 words·1 min
From Zero to Hero: Claude-3.5 Tops GPT-4
·100 words·1 min
When 'C' Speeds: GPT-2 Training Cut from 14 Hours to 90 Minutes
·45 words·1 min
Phi-3 14B: Small Model, Big MMLU—Rivaling Llama3 70B!
·28 words·1 min
AI: 'Complex' and 'Unique'? Challenge Accepted
·25 words·1 min
Your Model's IQ Won't Impress LMSys
·48 words·1 min
Go Big or Go Home: Scaling Up Go Models by 100,000X
·51 words·1 min
Text Leaderboards? So Passé—Enter Multimodal AI with Planning
·25 words·1 min
100 TFLOPs vs. 2 Human Hours: Measuring Work in FLOPs
·413 words·2 mins