ExaAI launches semantic search over 300M+ papers with two new benchmarks
yoimnotkesku · x · 2026-07-23
ExaAI says it has launched semantic search over 300M+ papers with a custom retrieval system built for scientific knowledge.
- The post highlights two new research paper benchmarks released alongside the product.
- In internal evals, Exa says its system is far more accurate than Google Scholar-style traditional tools.
- The framing is that future AI agents will need stronger search over scientific literature to accelerate discovery.
More from Companies & People
- Multica says community PR review is so costly it still has 400+ unmerged requests — jiayuan_jy · 2026-07-23
- Post says the U.S. led open models first, then let closed models take over — cocktailpeanut · 2026-07-23
- For enterprise AI agents, the first question is ownership and governance, not Copilot Studio vs. Foundry — WirelessLife · 2026-07-23
- WAIC speaker says world models are gaining real momentum in China — smtabatabaie · 2026-07-23
- User criticizes Anthropic strategy: RLHF unbearable, Chinese models more practical — StewartalsopIII · 2026-07-23
- AI-culture joke says you now have to LARP to succeed — KadriJibraan · 2026-07-23