Thanks for reading. You can follow me on X (@nand2mario) for updates, or use RSS.
▲ 截图来自小红书@去海边喝酒，推荐阅读旺商聊官方下载获取更多信息
。关于这个话题，同城约会提供了深入分析
Testing LLM reasoning abilities with SAT is not an original idea; there is a recent research that did a thorough testing with models such as GPT-4o and found that for hard enough problems, every model degrades to random guessing. But I couldn't find any research that used newer models like I used. It would be nice to see a more thorough testing done again with newer models.
Последние новости，这一点在91视频中也有详细论述
But look at what's happening now. Someone needs information, they open ChatGPT or Claude or Perplexity, they ask a question in natural language, they receive a comprehensive answer immediately with sources cited. No clicking through multiple websites. No comparing different perspectives. No scanning search results pages. The AI synthesizes information and delivers a direct answer, fundamentally changing the discovery process.