Top all-time · #12236
Elicit: AI for research & decision-making
Company blog · blog.elicit.com/blogaiscience
Elicit: AI for research & decision-making is the company blog at blog.elicit.com, writing about ai and science. Since 2023, 6 different Hacker News readers have linked it 15 times, most often “Living documents as a UX pattern in AI”. No feed was found, so read it on the site itself.
Too few sampled comments (2) to say how often HN recommends it.?
Why HN links it
HN readers link this blog for posts on Elicit's AI research work, including factored cognition and verification methods meant to reduce hallucinated results in science-related AI tools.
Summarised by Claude from a sample of 2 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Elicit helps you synthesize evidence, understand the landscape, design programs and experiments, draft proposals, and weigh tradeoffs. Trusted by over 7 million researchers and 8 of the top 20 pharmaceutical companies
Most-linked posts?
- Living documents as a UX pattern in AI2 people · 2 mentions · first linked 2024-05-23
What Hacker News says?
Elicit ( https://elicit.com/careers ) | Oakland, CA and Hybrid | Frontend, AI, and Full-stack software engineering roles. Elicit is automating high-quality reasoning so that we can help the world make more breakthroughs in every domain: from climate change to the gut microbiome to longevity and economic policy. We’ve scaled to over 200,000 monthly users purely by word of mouth and recently crossed $1.5MM in annual r…
Comment linking /living-documents-ai-ux/
on “Ask HN: Who is hiring? (July 2024)”Submitted From grep to SPLADE: a journey through semantic search as a story · 70 points
HN discussionThis is why for domains like science, tools like Elicit are so needed [1]. They've been doing some interesting work on factored cognition to avoid these sort of hallucinations [2]. 1: https://elicit.com/ 2: https://blog.elicit.com/factored-verification-detecting-and-...
Comment linking /factored-verification-detecting-and-reducing-hallucinations-in-frontier-models-using-ai-supervision/
on “ChatGPT generates fake data set to support scientific hypothesis”Submitted Notebooks: A New Way to Analyze Papers in Elicit as a story · 11 points
HN discussionSubmitted Living documents as a UX pattern in AI as a story · 10 points
HN discussionSubmitted Trust at scale: Auto-evaluation for high-stakes LLM accuracy as a story · 6 points
HN discussionSubmitted Elicit Research launches support for Clinical Trials as a story · 5 points
HN discussionSubmitted Discovering alignment windfalls reduces AI risk as a story · 5 points
HN discussionSubmitted Scaling your impact: A polynomial model of career growth as a story · 3 points
HN discussionSubmitted How we launch a user-facing feature every week as a story · 3 points
HN discussionSubmitted Elicit Reports as a story · 2 points
HN discussionSubmitted Elicit Systematic Review as a story · 2 points
HN discussionSubmitted Against RL: The Case for System 2 Learning as a story · 2 points
HN discussionSubmitted Build a search engine, not a vector DB as a story · 2 points
HN discussionSubmitted Ought announces Elicit, a tool to automate scientific literature review as a story · 1 points
HN discussion