大模型评估排障指南 | 关于 LaTeX 公式解析
"模型评估" 相关文章
AI companies' eval reports mostly don't support their claims
AI疯狂进化6个月，一张天梯图全浓缩，30+模型混战，大神演讲爆火
奥特曼ChatGPT用法错了，最新研究：要求“直接回答”降低准确率，思维链提示作用也在下降
The Decreasing Value of Chain of Thought in Prompting
苹果最新研究：现有 AI 大模型“更像是在记忆，而非真正的推理”
DeepSeek-r1-0528 Did Not Have a Moment
昇腾NPU上基于MindIE服务的AIME和MATH500测评方案
Claude 4 核心成员：2027年，AI将自动化几乎所有白领工作
New website analyzing AI companies' model evals
Meta Researchers Introduced J1: A Reinforcement Learning Framework That Trains Language Models to Judge With Reasoned Consistency and Minimal Data
从BGE到 CLIP，从文本到多模态，Embedding 模型选型终极指南
It Is Untenable That Near-Future AI Scenario Models Like “AI 2027” Don't Include Open Source AI
Hacker News热文｜“Jagged AGI”：o3和Gemini 2.5究竟是不是AGI？
Use custom metrics to evaluate your generative AI application with Amazon Bedrock
68页论文再锤大模型竞技场！Llama4发布前私下测试27个版本，只取最佳成绩
GPT-4o Sycophancy Post Mortem
AI圈惊天丑闻，Meta作弊刷分实锤？顶级榜单曝黑幕，斯坦福MIT痛斥
68 页论文再锤大模型竞技场：Llama4 发布前私下测试 27 个版本，只取最佳成绩
Study accuses LM Arena of helping top AI labs game its benchmark
