本文为机器翻译
展示原文

端到端测试时训练 (TTT-E2E) 解决了人工智能领域最棘手的问题之一:LLM 长上下文记忆。热烈祝贺团队发布!我们很高兴能用我们的人工智能基础设施支持这项工作,并期待看到更多基于 Hyperbolic 的前沿研究。

Karan Dalal
@karansdalal
01-13
LLM memory is considered one of the hardest problems in AI. All we have today are endless hacks and workarounds. But the root solution has always been right in front of us. Next-token prediction is already an effective compressor. We don’t need a radical new architecture. The
来自推特
免责声明:以上内容仅为作者观点,不代表Followin的任何立场,不构成与Followin相关的任何投资建议。
喜欢
收藏
评论