Original Summary

The world economy around us depends on complex financial work. How well can AI do it?<p>We(a team of ex-EY employees) built FAB - Finance Agents Benchmark, testing AI Agents on the work behind financial due diligence. Agents can find the relevant facts, but still struggle to carry them through to a complete, reliable analysis.<p>We’ll keep expanding FAB to more companies and testing more models. Building and running this benchmark isn’t cheap, so we’re scaling it in stages.<p>The benchmark is public.<p>GitHub: Hugging Face: <a href="https:&#x2F;&#x2F;github.com&#x2F;SecondState-ai&#x2F;finance-agents-benchmark" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;SecondState-ai&#x2F;finance-agents-benchmark</a> data room and tasks: <a href="https:&#x2F;&#x2F;huggingface.co&#x2F;datasets&#x2F;secondstate&#x2F;finance-agents-benchmark" rel="nofollow">https:&#x2F;&#x2F;huggingface.co&#x2F;datasets&#x2F;secondstate&#x2F;finance-agents-b...</a>

  • 情报分类：技术学习与提效
  • 分类依据：内容涉及技术、AI、软件工具或工程实践
  • 信息来源：Hacker News 新项目
  • 发布时间：2026/9/28 14:34:40