FutureHouse的封面图片
FutureHouse

FutureHouse

生物技术研究

San Francisco，CA 4,088 位关注者

A philanthropically-funded moonshot focused on building an AI Scientist.

查看职位 关注

关于我们

Our 10-year mission is to build semi-autonomous AIs that can scale scientific research, to accelerate the pace of discovery and to provide world-wide access to cutting-edge scientific, medical, and engineering expertise.

网站
https://www.futurehouse.org
所属行业
生物技术研究
规模
2-10 人
总部
San Francisco，CA
类型
非营利机构
创立
2023

地点

FutureHouse员工

查看全部员工

动态

  • FutureHouse转发了

    查看Michael Skarlinski的档案
    Michael Skarlinski

    Technical Staff @ FutureHouse

    We're thrilled to announce PaperQA2 is the top scoring system on RAG-QA Arena's science benchmark. RAG-QA Arena tests a system's ability to extract information from large corpora (1,404 science questions from 1.7M documents). PaperQA2 scores 12.4% higher than the closest system tested. This is the first benchmark we've measured directly against competitive systems, like Cohere or Contextual.ai. You can read more about our methods, and how to access PaperQA2 here: https://lnkd.in/epdbeZeM Thanks to Joaquín Polonuer for all his hard work in putting these results together.

    • 该图片无替代文字
  • 查看FutureHouse的组织主页
    FutureHouse

    4,088 位关注者

    One half of an AI scientist is rejecting or accepting hypotheses. ScienceMachine and FutureHouse just put out ~300 novel hypotheses from ~50 published papers along with ground-truth data. Humans take 4.2 hours to solve these and frontier models get 10-20% correct. This is like SWE-bench for comp bio - so if you get a good score, you make new discoveries instead of closing issues in Django's github. Here's an example hypotheses (+ a dataset) Truncating ASXL1 mutations will lead to specific gene expression changes in blood that reflect alterations in hematological processes, such as T cell and neutrophil activation. And the open answer ground-truth: Gene ontology (GO) analysis of differentially expressed genes (DEGs) in Bohring-Opitz syndrome blood samples revealed significant enrichment for hematological processes, including T cell activation (p-adj = 3.23E-8) and neutrophil activation (p-adj = 1.90E-5). This suggests that ASXL1 mutations notably impact immune-related pathways in blood samples. It also comes in T/F and MCQ variants, if you like that kind of eval. See the benchmark here: https://lnkd.in/gKhrjRBE The arxiv paper: https://lnkd.in/gwBWGrgs And an overview: https://lnkd.in/grSzZHRv

  • 查看FutureHouse的组织主页
    FutureHouse

    4,088 位关注者

    Today, in partnership with?ScienceMachine, we're releasing BixBench - a benchmark for evaluating AI agents on real-world bioinformatics tasks Biological data analysis is one of the fastest-progressing and most promising fields for AI-driven automation in science. Here, we provide a rigorous framework for assessing the performance of LLM-based AI agents in computational biology. We've curated a dataset of 53 analytical scenarios and 296 open-ended questions, covering real-world bioinformatics challenges. Additionally, BixBench includes a comprehensive evaluation framework for biological data analysis capabilies and an open-source agent environment, enabling LLMs to execute these tasks. Read more on our blog. https://bit.ly/4km2zdd

    • 该图片无替代文字
  • 查看FutureHouse的组织主页
    FutureHouse

    4,088 位关注者

    We're hosting up to 40 Bay Area hackers attending the 2024 LLM Hackathon for Applications in Materials and Chemistry onsite at our brand new space in the Dogpatch in San Francisco on May 8 and May 9. Registrations are still open, reserve your spot quickly before they are gone. Register for the hackathon via Eventbrite here https://lnkd.in/gXKvKuYt and then register for access to our San Francisco venue if you want to hack with others onsite https://lnkd.in/gZiGGeUS

    查看Ben Blaiszik的档案
    Ben Blaiszik

    Globus Labs | AI for Science | Materials Data Facility | Garden AI |@BenBlaiszik

    ?? Unlocking New Frontiers: 2nd LLM Hackathon for Applications in Materials and Chemistry ?? Join us on May 8-9th for the 2nd Large Language Model Hackathon for Applications in Materials and Chemistry! Last year's hackathon showcased the promise of LLMs, with participants showcasing new projects in structured information extraction, property prediction, novel software interfaces, education, and more. This year, with even more powerful models at our disposal, we invite you to push the boundaries of what's possible. ?? Paper from last year's event: https://lnkd.in/gxayv2j7 ?? Registration: https://lnkd.in/gs7VjCtH Whether you join us in person or virtually, you'll have the opportunity to network, learn, and contribute to cutting-edge research that could transform the future of materials and chemistry. Don't miss this chance to be part of something extraordinary. Registration is open now. Stay tuned for more details on our featured speakers, judges, and in-person locations! Save the date: May 8-9th, 2024. Together, let's unlock new frontiers in materials and chemistry research! Stay tuned for more details on our featured speakers, judges, and in-person locations! Save the date: May 8-9th, 2024. Together, let's unlock new frontiers in materials and chemistry research! Registration: https://lnkd.in/gs7VjCtH

    • 该图片无替代文字

相似主页

查看职位