(评论)
(comments)

原始链接: https://news.ycombinator.com/item?id=43765207

Hacker News 最新 | 过去 | 评论 | 提问 | 展示 | 招聘 | 提交 登录 单个AI模型能否推进任何科学领域? (lanl.gov) 6 分 LAsteNERD 1 小时前 | 隐藏 | 过去 | 收藏 | 1 评论 Tycho 5 分钟前 [–] 应该可以通过在历史数据集上训练LLM,然后探测它们是否能够重新发现其训练数据截止日期后发现的东西来进行回测。什么类型的提示可以促使它们取得突破。 回复 加入我们,参加 6 月 16-17 日在旧金山举办的 AI 初创企业学校! 指导原则 | 常见问题 | 列表 | API | 安全 | 法律 | 申请 YC | 联系我们 搜索:

相关文章
  • (评论) 2025-04-16
  • (评论) 2025-04-22
  • (评论) 2025-03-26
  • (评论) 2025-03-18
  • (评论) 2025-03-23

  • 原文
    Hacker News new | past | comments | ask | show | jobs | submit login
    Can a single AI model advance any field of science? (lanl.gov)
    6 points by LAsteNERD 1 hour ago | hide | past | favorite | 1 comment










    Should be possible to backtest by training LLMs on historic datasets and then probing them to see if they can re-discover things that were discovered after their training data cut-off. What sort of prompts could push them to make a breakthrough.






    Join us for AI Startup School this June 16-17 in San Francisco!


    Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact



    Search:
    联系我们 contact @ memedata.com