Log inSign up
Elicit
1,689 posts
Image
user avatar
Elicit
@elicitorg
AI for scientific research elicit.com • Demos demos.elicit.com • Jobs elicit.com/careers
San Francisco, CA
elicit.com
Joined October 2020
47
Following
14K
Followers
  • user avatar
    Elicit
    @elicitorg
    14h
    Elicit's MCP now runs inside Claude. Here's an example of what that looks like. We handed Claude a research write-up with claims that needed validation. Claude searches Elicit's corpus, checks each claim against the evidence, and returns the papers that back the claims. Where a
    Image
    00:00
    1K
  • user avatar
    Elicit
    @elicitorg
    17h
    Elicit is now in Anthropic's Connectors Directory. You can find it and connect in one click. Once connected, Claude can search 138M+ papers and run grounded literature reviews without leaving the chat. Ask it to read your experiment results and find papers studying similar
    Image
    671
  • user avatar
    Elicit
    @elicitorg
    20h
    We asked Elicit to check this, and it's true! Several high-quality studies show that not having AC in hot conditions reduces cognitive performance. Elicit looked through 150 papers, found the best ones and made this graph.
    Image
    Image
    user avatar
    Trung Phan
    Workweek 🤝
    @TrungTPhan
    Jun 23
    Lee Kuan Yew: “Air conditioning was a most important invention for us, perhaps one of the signal inventions of history. It changed the nature of civilization by making development possible in the tropics. Without air conditioning you can work only in the cool early-morning
    930
    user avatar
    Elicit
    @elicitorg
    20h
    elicit.com/agent/aaca7e8e…
    237
  • user avatar
    Elicit
    @elicitorg
    Jun 24
    Evaluation is quickly becoming one of the most important challenges in AI development. Our Eval team is hosting a fireside chat on what evaluation looks like in the real world. We'll cover: - How evaluation has changed as models have gotten more capable. - When to pick an
    Image
    671
  • user avatar
    Elicit
    @elicitorg
    Jun 18
    Despite billions in R&D, oncology target selection remains remarkably qualitative. At Bio-IT World 2026, our CEO Andreas Stuhlmüller shared how we're thinking about this problem. The idea: Turn the target review into a living causal model. The model maps out what has to be true
    1K
  • Elicit reposted
    user avatar
    Jungwon
    @jungofthewon
    Jun 18
    We built a reasoning native programming language because LLMs break at scale
    user avatar
    The Cognitive Revolution Podcast
    @CogRev_Podcast
    Jun 18
    🧠NEW EPISODE: @stuhlmueller and @jungofthewon , co-founders of @elicitorg , are back on The Cognitive Revolution with @labenz after two years — and the mission hasn't moved an inch: radically improve the quality of reasoning behind high-stakes decisions. What's changed is how
    Image
    00:00
    1.3K
  • Elicit reposted
    user avatar
    The Cognitive Revolution Podcast
    @CogRev_Podcast
    Jun 18
    🧠NEW EPISODE: @stuhlmueller and @jungofthewon , co-founders of @elicitorg , are back on The Cognitive Revolution with @labenz after two years — and the mission hasn't moved an inch: radically improve the quality of reasoning behind high-stakes decisions. What's changed is how
    Image
    00:00
    3.8K
  • user avatar
    Elicit
    @elicitorg
    Jun 17
    A fair question about any data extraction tool: can you actually trust what it pulls? Farhad Shokraneh, PhD, an SLR methodologist at Systematic Review Consultants ran a scoping review for a policy brief and used Elicit to check the accuracy of each data point. Below he shares his
    Image
    496
  • user avatar
    Elicit
    @elicitorg
    Jun 16
    The recording from yesterday's webinar is live: What's Next in AI for Life Sciences: Evaluating Superhuman AI. AI is outpacing the evaluation playbook. Accuracy, precision, and recall work for simple tasks, but break down once AI takes on evidence synthesis, multi-step
    670
    user avatar
    Elicit
    @elicitorg
    Jun 16
    Elicit co-founder and COO Jungwon Byun breaks down how to evaluate AI for evidence and research with more rigor: - Where old evaluation methods fail - A practical framework for evaluating superhuman AI - How to catch confirmation bias and sycophancy in AI-written reports - How
    277
  • Elicit reposted
    user avatar
    Pradyumna (in Bay Area)
    @PradyuPrasad
    Jun 12
    The more I think about it, the more bullish I am on @elicitorg in a world of very good models. We're going to do so much good reasoning
    1.3K
  • user avatar
    Elicit
    @elicitorg
    Jun 12
    Monday's webinar is officially at capacity. The response to "What's Next in AI for Life Sciences: Evaluating Superhuman AI" has been incredible. Thank you to everyone who registered. If you didn't get a spot, we've got you covered. Fill out the form below to receive the
    Image
    412
  • user avatar
    Elicit
    @elicitorg
    Jun 11
    We're heading to DIA from June 14-18 in Philly. DIA brings together key stakeholders in life sciences across regulatory, clinical, safety, medical affairs, quality, and policy. We want to meet as many of you as we can and hear how AI is actually changing the day-to-day of your
    Image
    351
  • user avatar
    Elicit
    @elicitorg
    Jun 10
    Can Elicit's full-text screening recall every relevant paper in a systematic review? We evaluated Elicit's recall using 74 Cochrane reviews and 377 studies. The results: 99.5% Paper-level recall 94.8% Per-criterion accuracy For teams running systematic reviews, this means
    Image
    1.3K
    user avatar
    Elicit
    @elicitorg
    Jun 10
    Methodology, edge cases, and per-MeSH-area performance → elicit.com/blog/evaluatin….
    Image
    Evaluating Elicit’s Systematic Literature Review Capabilities - Elicit
    From elicit.com
    494

New to X?

Sign up now to get your own personalized timeline!

Create account

By signing up, you agree to the Terms of Service and Privacy Policy, including Cookie Use.

Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
Don't miss what's happening
People on X are the first to know.
Log inSign up