Elicit

Spent hours spent curating, collecting, and summarizing research in college. No regrets, but now there's an #AI research assistant for that: Elicit: https://lnkd.in/eF4N-V_9 #AIedu #research

Have a look at Elicit , the AI-powered research assistant, revolutionizes how you tackle research papers. Up to 80% time savings in systematic reviews and data extraction. Unmatched accuracy and deeper insights into your research. Curious? Elicit offers a free plan to help you explore its powerful capabilities. #AI #ResearchEfficiency #Innovation #Elicit #Productivity

Last week we launched Elicit Reports and claimed they provide the best research overviews for actual researchers -- better than other "Deep Research" tools. Today, we’d like to share the methodology and data behind this claim. ?? Link to full post: https://lnkd.in/gadJ263p 1/ We recruited 17 PhD-level professional researchers with backgrounds across neuroscience, speech therapy, economics, organizational psychology, information studies, ecology, and engineering. 2/ We asked these evaluators to compare Elicit to competitors in their area of expertise. They asked questions like: What are the comparative energy efficiencies of renewable energy sources for powering large-scale artificial intelligence and machine learning data centers? https://lnkd.in/gGR8_vRa 3/ The evaluators compared Elicit against: ? ChatGPT (o3-mini-high) with Deep Research ? Perplexity Deep Research ? Google Gemini Advanced 1.5 Pro with Deep Research ? Undermind ? Ai2 Scholar QA ? GPT-4o ? Claude 3.5 Sonnet ? Perplexity Pro ? Consensus ? Scite The last five were dropped after scoring low in early evaluations. 4/ These researchers evaluated 29 Elicit reports, and 120 reports across competitor tools. n=28 for ChatGPT Deep Research n=26 for Perplexity Deep Research n=11 for Google Gemini n=29 for Undermind n=26 for Ai2 Scholar QA 5/ We asked evaluators to give a general rating of each report on a scale of 0 to 10, where 0 was defined as “useless, low quality” and 10 as “very useful, high quality.” 6/ We asked evaluators to estimate how many hours the tool would save them when writing a systematic review. Estimates varied substantially, from 0 to 960 hours, equivalent to 6 months of full-time work at 40 hours/week. Thus the mean estimated time saved is skewed by high values and we report the median instead. 7/ We asked: “How good is the main answer of the report? Look at whatever is the closest to a ‘main answer’” for three metrics: accuracy, usefulness, and how well it answers the research question. 8/ Besides small sample size, our analysis is subject to the following limitations: ? We paid the evaluators, which may have biased their results. However, evaluators (a) did not hesitate to rate competitors more highly at times and (b) justified all their ratings, which leads us to believe that this is not driving results. ? We performed several rounds of evaluations with the same researchers instead of hiring new ones each time. Thus they saw improvement between versions of Elicit Reports, which could also have biased results. ? Though our evaluators are skilled professionals with research experience, their usage of Elicit and competitors may not be fully representative of other users or the full range of capabilities of each tool. 9/ For the full evaluation, including qualitative feedback, check out https://lnkd.in/gadJ263p

Don't sleep on Elicit . I just used it to answer a nagging question, "are there benefits using fresh milled wheat vs store bought?" I am no researcher... as you can tell from my question ???? The updated tools from Elicit helped me focus my question and delivered a response, "Fresh vs. Store-Bought Flour: Glycemic and Digestive Effects." It then gave me its summary and further drilled into characteristics across the cited research. Now onto the next step for me - reading the research of most relevance to me, refining my question, and reading more research. What do you do to create a great research question?

Excited to announce our Series A and the launch of Elicit Reports, fully-automated research overviews for actual researchers. Based on external evaluation, we found that Elicit Reports produce higher quality research summaries and save more time than any other “deep research” tool on the market, including ChatGPT Deep Research. Also, we are actively hiring PMs now, so please DM me if interested or know someone who is a good fit to scale up good reasoning! https://elicit.com/careers?

Congratulations to Elicit on their $22M Series A round, co-led by Footwork and Spark Capital. Elicit is the leading AI platform for research, with the mission of deploying AI to radically increase good reasoning in the world. If you're interested in joining this pursuit, check out the careers page at elicit.com/careers.

the group chat is buzzing about Elicit's new Reports – this is from a low-profile but super-savvy user I know well: "I cannot emphasize enough how much better Elicit is than Deep Research from any company with respect to academic/medical topics" proud to be a (tiny) angel investor in a company that's achieving great results with a principled approach! congrats Jungwon Byun Andreas Stuhlmüller & team!

Today, Elicit announces its $22M Series A, and the launch of Elicit Reports: fully-automated research overviews. Ask a research question & Elicit will conduct a rapid review (search, screening, data extraction) to write the Report. Try it for free at elicit.com. Very excited for us at Footwork to work with founders Andreas Stuhlmüller and Jungwon Byun, and the cracked team they've assembled to pursue Elicit's mission: scale up good reasoning. Mike Smith and I are delighted to co-lead this round alongside Fraser Kelton at Spark Capital with existing investors Seth Bannon at Fifty Years, Vishal Maini at Mythos Ventures, and Lan Xuezhao at Basis Set. More on the story and why we invested in the comment link.

I am thrilled to share that Spark Capital is co-leading a $22m investment in Elicit -- www.elicit.com. Already, Elicit's AI Research Assistant automates the ability to understand the state of science. We are excited for a world where Elicit automates the scientific method. Launching today, Elicit Reports are the best way to understand the state of science. AI's ability to automate work is already profound -- PhDs estimate that Elicit saves them 16 hours of research per report. Give Elicit a question and the product gathers papers that could be of interest, creates its own screening criteria and filters the papers based on this, extracts data from the curated set of papers, and synthesizes all of the findings into a report. All autonomously. Here's an Elicit Report examining the efficacy of online CBT interventions vs traditional CBT for anxiety: https://lnkd.in/grXhCfbi Today, Elicit is saving hours of PhD-level research time. Their product roadmap will see AI automate research. Co-founders Andreas Stuhlmüller and Jungwon Byun and their stellar team impressed us with their ability to weave together engineering, machine learning, and product design to deliver a great product experience. We are excited to be co-leading this round with Nikhil Basu Trivedi and Mike Smith from Footwork with participation from current investors like Seth Bannon at Fifty Years, Basis Set, and Mythos Ventures.

Elicit Reports are a sign of things to come - transparent, systematic reasoning applied at scale. With the Series A, we'll expand beyond academic research and automated literature review We'll apply the same approach to become the standard for evidence-based decision-making