Meta's LeCun Introduces SAI: A Measurable Alternative to AGI
LLMs
12 posts in LLMs
Reasoning Overthinking Solved: SAGE Cuts Tokens 44% While Improving Accuracy
175% Faster Prefill with Better Accuracy: ConceptMoE's Adaptive Token Compression for MoE
15-Hour Agent Runtimes Solved: Idea2Story Precomputes Research Knowledge Offline
Tsinghua Researchers Show Diffusion LLMs Reason Better When You Take Away Their Flexibility
SimpleMem gives LLM agents 30x cheaper memory with 26% better recall
Agent Memory Fragmentation Solved: EverMemOS Achieves 93% on LoCoMo via Engram-Inspired Lifecycle
4 Percentage Points Better Accuracy With Rude Prompts: How Tone Affects GPT-4o Performance
6% Better Math Reasoning in Fewer Tokens: Multiplex Thinking Merges Multiple Paths into One
Gold Medal at IMO and IOI: DeepSeek-V3.2 Matches GPT-5 with Open Weights
Why Reasoning Models Cheat on Efficiency: TNT's Fix Cuts Tokens 50%
Why Chain-of-Thought Works: Researchers Find a Single 'Reasoning Switch' in LLMs
