Tom Zhi
@tomzhi
ID: 20913207
https://tomzhi.wordpress.com 15-02-2009 14:46:58
8,8K Tweet
450 Followers
1,1K Following
I'm seeing quite a bit of comment about this, so I want to make a couple of points. I'm not owed eternal agreement from any actor who once played a character I created. The idea is as ludicrous as me checking with the boss I had when I was twenty-one for what opinions I should
告别 AI “一家之言”,打造你的专属 LLM 决策委员会,Andrej Karpathy 开源了一个多模型评审会的demo,体验链接见最后👇 这个系统的核心是让 DeepSeek、Qwen、Grok 等模型同台辩论,引入了学术界的“同行评审”机制,用魔法打败魔法 核心亮点: 1. 第一阶段是全员提案:多模型并行输出,打破单一视角局限 2.
Max For AI 我觉得Anthropic在最开始有大规模蒸馏OPEN AI的行为,刚开始模型能力很差,跟着OpenAI 的进步才进步的,然后他们将核心差异转到代码上,才有了后面的进步。