return to table of content

Launch HN: Undermind (YC S24) – AI agent for discovering scientific papers

setgree
7 replies
2d

Very cool, and very relevant to my life -- I am currently writing a meta-analysis and finishing my literature search.

I gave it a version of my question, it asked me reasonable follow-ups, and we refined the search to:

I want to find randomized controlled trials published by December 2023, investigating interventions to reduce consumption of meat and animal products with control groups receiving no treatment, measuring direct consumption (self-reported outcomes are acceptable), with at least 25 subjects in treatment and control groups (or at least 10 clusters for cluster-assigned studies), and with outcomes measured at least one day after treatment begins.

I just got the results back: https://www.undermind.ai/query_app/display_one_search/e5d964....

It certainly didn't find everything in my dataset, but:

* the first result is in the dataset.

* The second one is a study I excluded for something buried deep in the text.

* The third is in our dataset.

* The fourth is excluded for something the machine should have caught (32 subjects in total), but perhaps I needed to clarify 25 subjects in treatment and control each.

* The fifth result is a protocol for the study in result 3, so a more sophisticated search would have identified that these were related.

* The sixth study was entirely new to me, and though it didn't qualify because of the way the control group received some aspect of treatment, it's still something that my existing search processes missed, so right away I see real value.

So, overall, I am impressed, and I can easily imagine my lab paying for this. It would have to advance substantially before it was my only search method for a meta-analysis -- it seems to have missed a lot of the gray literature, particularly those studies published on animal advocacy websites -- but that's a much higher bar than I need for it to be part of my research toolkit.

physicsguy
2 replies
1d11h

For a systematic review/meta analysis you’d be expected to document your search strategy, exclusion criteria, etc anyway wouldn’t you? That’d preclude using a tool like this other than as a sense check to see if you needed to add more keywords/expand your search criteria anyway.

My wife does that for her day job (in the U.K. national healthcare system) and the systematic reviews have to be super well documented and even pre-registered on a system called PROSPERO. The published papers always have the full search strategy at the end.

setgree
1 replies
1d5h

I was planning to say "I used an AI search tool" and cite undermind.ai in my methods section. I think that won't raise any eyebrows in the review process but we'll see.

physicsguy
0 replies
1h57m

Have a look at the PRISMA reporting guidelines

tom_hartke
1 replies
2d

For a meta-analysis, you might want to try the "extend" feature. It sends the agent to gather more papers (we only analyze 100 carefully initially), so if your report might say "only 55% discovered", could be useful.

(Also, if you want, you can share your report URL here, others will be able to take a look.)

setgree
0 replies
2d

Thanks, I added my URL

Mkengine
1 replies
1d10h

I only have some experience writing normal papers, so just out of interest, could you elaborate what your usual search routine for a meta-analysis is?

setgree
0 replies
1d5h

There's a whole established process for this, see here for a textbook chapter https://training.cochrane.org/handbook/current/chapter-04

However, because I'm writing a methods-focused review -- we only look at RCTs meeting certain (pretty minimal) criteria relating to statistical power and measurement validity -- what I'm doing is closer to a combination of review of previous reviews (there have been dozens in my field) and a snowball search (searching bibliographies of papers that are relevant). I also consulted with experts in the field. however, finding bachelor's theses has been challenging, but many are actually relevant, so undermind was helpful there.

passwordoops
6 replies
1d7h

"manually dig through papers on Google Scholar for hours."

Is exactly how you gain expertise in a field and/or find those subtle gaps in knowledge that are the seeds of real breakthrough

fullstackchris
3 replies
1d6h

but the actual manually digging is not - reading the paper is, and the faster you can get some 10-20 papers, the better off you are

passwordoops
1 replies
1d5h

If someone is at the level where they need 10-20 papers to understand a topic, they are not at the level where they are even capable of asking a specific enough question. In their case, doing the hard work and sifting though 100s of papers is the best way to train themselves to think critically and thoroughly evaluate whether a paper is relevant to them.

There is also the real fact that the greatest discoveries usually come from obscure corners and reading as much as you can is the only way to explore those corners. Otherwise, you're just refining what was done before you

llm_trw
0 replies
1d3h

I have no idea how old you are, but being in my 40s and needing to get results quickly I don't really care to learn the minutia for whatever type of stamp collecting is important for the project I'm working on now.

DonsDiscountGas
0 replies
1d5h

Reading papers that turn out to be irrelevant to the specific problem at hand is probably the biggest time sink; it's also probably an important source of general education. But good academics presumably know the importance of keeping an open mind and general learning.

tom_hartke
0 replies
1d3h

I think we associate learning/discovery with those moments because they happen together, not because they're causally related.

I think this is somewhat equivalent to how we used to have to learn 100 different integrals and derivatives in calculus. That's somewhat helpful. I learned to see patterns in math like that, the same way I learned a decent bit by browsing irrelevant abstracts and follow citation trails. But physically memorizing 100s of integrals is mostly a waste, and so are the irrelevant abstracts. You'll be much better at math (and hopefully science) if you can learn ~10 key integrals or read ~10 abstracts, and then spend the rest of your time understanding the high level patterns and implications by talking with an expert. Just like I can now ask GPT-4 to explain why some integral formula is true, which ones are related, and so on.

And that's the last point - these literature search tools aren't developing in isolation. We will get to have a local "expert" to discuss what we find with. That changes the cost-benefit analysis too.

jpmattia
0 replies
1d4h

"manually dig through papers on Google Scholar for hours."

The old dinosaurs on HN are snickering about the word "manual" here, having blown days pawing through the library stacks.

sitkack
5 replies
1d23h

How is this different than the work that semantic scholar is doing around AI?

tom_hartke
4 replies
1d22h

Semantic Scholar seems more focused on 1. being the data provider/aggregator for the research community, and 2. long term, I think they plan to develop software at the reading interface that learns as a researcher uses it to browse papers (a rich PDF reader, with hyperlinks, TLDRs, citation contexts, and a way to track your interactions over time, and remind you of what you've seen or not).

Their core feature now is a fast keyword search engine, but they also have a few advanced search features through their API (https://api.semanticscholar.org/api-docs/) like recommendations from positive/negative examples, but neither KW search nor these other systems are currently high enough quality to be very useful for us.

FYI our core dataset for now is provided by Semantic Scholar, so hugely thankful for their data aggregation pipeline and open access/API.

shashkingregory
2 replies
1d21h

I've used undermind for literature search and it was very precise! Thanks for the product! I wonder how you plan to extend the search to full paper content (will Semantic Scholar api allow this) - and do you plan to connect more datasets (which ones)? (many of them are paid...)

jramette
1 replies
1d19h

We'll certainly be able to include open access full texts, which is already a substantial fraction of the published papers, and a growing fraction too, as the publishing industry is rapidly moving toward open access. Paywalled full text search would require working with the publishers, which is more involved.

shashkingregory
0 replies
1d8h

Great! I can definitely ask undermind for an overview paper of the scientific information landscape, unless you have a favourite in quick access to share?

sitkack
0 replies
1d22h

Do you plan on adding an API? I already have an inhouse knowledge discovery, annotation and search system that could be augmented by your service. Not super critical at this point, but a would be nice.

And yes, Semantic Scholar is a wonderful part of the academic commons. Fingers crossed they don't go down the jstor/oclc path.

danpalmer
4 replies
1d14h

So does this undermine academics? the research industry? the academic publishing industry? Who exactly is being "undermined" by this AI product?

With the current attitudes to AI, the name feels a little tone deaf being so easily mistaken for AI undermining people.

tom_hartke
1 replies
1d14h

Emphasis is meant to be on "mind", like supporting better reasoning, but point taken.

danpalmer
0 replies
1d13h

Yeah I get it, but if someone said "check out undermind", I could easily hear it as "check out undermined", as they are pronounced identically for most English language speakers.

SubiculumCode
1 replies
1d14h

undermind

danpalmer
0 replies
1d13h

"being so easily mistaken"

viraj_shah
3 replies
1d20h

Here is an open source tool for summarizing Arxiv papers: https://summarizepaper.com/

tom_hartke
0 replies
1d3h

Hadn't seen that. Very complementary. We don't address staying up to date or pull in community value metrics (other than total citations). It's a somewhat different goal to broadly gather emerging ideas and stay informed.

sirlunchalot
3 replies
1d19h

Very happy subscriber here, thank you for the tool. I do a lot of searching with it, however due to some changes in my life in the near future I will not need it as much so I wont be willing to spend $20 a month on it. So my question is, would you consider adding an option where one could pay per query rather than just per monthly subscription? I would love to use it for the occasional spark of curiosity when I want to know more about a certain topic without having to familiarise myself with the academic field surrounding it. Having a way for using undermind for situations like that would be truly amazing! Would gladly pay 1-2 or maybe even 3 dollars per extended query.

jramette
2 replies
1d19h

We've thought quite a bit about usage-based pricing, but found that doesn't work psychologically for most people. Generally, people seem happier by paying up front for access, then feel good about having the system available whenever they need it, rather then having to think through cost tradeoffs every time they want to do a search or use up credits. Please do reach out at support@undermind.ai though, we'd love to talk about a solution for you and get your feedback.

Jarwain
1 replies
1d18h

Have you considered the middle ground where there's a $10 tier ratelimited to X requests per timeperiod?

tom_hartke
0 replies
1d18h

Not a bad idea. Want to avoid too much complexity in pricing, though. Decision fatigue.

rjchint
3 replies
1d23h

How would you compare your product to elicit.ai?

In my opinion elicit has better looking UI and much more features and further along

tom_hartke
1 replies
1d23h

I think the biggest difference is our focus on search quality, and being willing to spend a lot on compute to do it, while they focus on systematic extraction of data from existing sources and on being fast. It's a bit of an oversimplification (they of course have search, and we also have extraction).

Feature-wise, we definitely have a lot of work to do :) What crucial pieces do you think we're missing?

lyjackal
0 replies
1d7h

From what I understand, that’s not the case. They are working on both. I’d be concerned about how you can differentiate and compete with them. They have a big head start

6gvONxR4sf7o
0 replies
1d15h

In my experience, elicit’s big weakness is accuracy.

mnode
3 replies
1d12h

I tried this with a question for an area I know well. It's pretty impressive but missed some key references.

I'd love to see limitations like this quantified and clearly flagged. Otherwise there's a danger that people may the assume results are definitive, and this could have the opposite outcome to that intended (much time spent working on something only to disocver it's been done already).

jramette
2 replies
1d12h

Yes, this is one of the most important aspects of the tool; in cases where you care about getting everything, make sure to take a look at the estimated percent of papers found at the bottom of the summary section. That gives you a sense of how complete the set of references likely are. We've tuned it to get around half of the total papers for the "median" user query on a first pass. If users desire, they can "extend" the search to have Undermind look for more papers. Additional caveat to remember with the current system is that it only accesses abstracts, so if you'd need to look in the full text to know a work is relevant, we wouldn't be able to catch it.

mnode
1 replies
1d12h

Thanks for clarifying. I didn't appreciate that it only searches abstracts. That might explain some of the missing references. Anyway, great work, will look forward to using it more.

jramette
0 replies
1d11h

Yep, will add in full texts as we can in the future. Let me know if the percent of papers found as an indication of an exhaustiveness measure was clear? Reach out to us at support@undermind.ai if you'd be willing to provide more feedback on your experience.

jpmattia
3 replies
1d3h

I was looking for a way to save the result page locally (ie offline). Maybe I need more coffee, but it did not look possible. So I'd add the ability to save the result (or at least make the button prominent).

But the fact I wanted to save a result is a good sign. Nice work!

tom_hartke
2 replies
1d3h

Just save the report url! It will persist.

Also, on the usual system if you're logged in (instead of the HN free link), all your searches automatically get saved on a "history" page.

jpmattia
1 replies
1d1h

I did see that, and maybe I should expand my comment. From the perspective of someone doing long-term research: Undermind is a startup and is subject to the vagaries of VC funding. Currently, AI is in fashion among VCs, but my guess is that the fashion will be shorter lasting than the usefulness of the search results. So having tried out the product and finding a nice literature list in a relatively new area for me, my first instinct was to store it among my org files because the probability that your company will disappear (or severely degraded upon acquisition) is high.

Anyway, I do not mean to detract from the accomplishment -- and I liked the product! So I hope you take the above feedback/nitpicking in the spirit it is intended.

tom_hartke
0 replies
22h22m

That makes sense. You should be able to right click - save as PDF and it will preserve the links, etc.

brainwipe
3 replies
2d

Independent researcher without academic address; can't get in. Best of luck.

tom_hartke
1 replies
2d

You should be able to try it here without loggin in: https://www.undermind.ai/query_app/promotion/ (set up for HN today). If not message support@undermind.ai and I'll set you up.

toisanji
0 replies
1d19h

can you fix it so anyone can get it, that sounds like a waste of time to block people.

zwaps
2 replies
1d13h

I really, really wish you would use a different citation format.

Arbitrary numbers are really the least information. At least use last names and years, so I can have some idea which paper you are talking about without scrolling back and forth.

tom_hartke
1 replies
1d13h

Thanks! That's helpful to hear. Honestly just did numbers because the LLM has no trouble remembering which is which, and it's easier to programmatically parse out the citations to build hyperlinks (compared to names/years, where little variations creep in).

IanCal
0 replies
1d4h

It could be a rendering thing rather than llm output. Output a number, pull the name/year when creating the page.

robwwilliams
2 replies
1d22h

Awesome! I just took you up on your offer and compared roughly similar questions using Claude 3.5 Sonnet and Undermind.

Claude 3.5 is reluctant to provide references—-although it will if coaxed by prompting.

Undermind solves this particular problem. A great complement for my research question —- the evidence that brain volume is reduced as a function of age in healthy cognitively normal humans. In mice we see a steady slow increase that averages out to a gain of 5% between the human equivalents of 20 to 65 years of age. This increase is almost linear as a function of log of age.

Here is the question that was refined with Undermind’s help:

I want to find studies on adult humans (ages 20-100+) that have used true longitudinal repeated measures designs to study variations in brain volume over several years, focusing on individuals who are relatively healthy and cognitively functional.

I received 100 ranked and lightly annotated set of 100 citations in this format:

[1] Characterization of Brain Volume Changes in Aging Individuals With Normal Cognition Using Serial Magnetic Resonance Imaging S. Fujita, ..., and O. Abe JAMA Network Open 2023 - 21 citations - Show abstract - Cite - PDF 99.6% topic match Provides longitudinal data on brain volume changes in aging individuals with normal cognition. Analyzes annual MRI data from 653 adults over 10 years to observe brain volume trajectories. Excludes populations with neurodegenerative diseases; employs true longitudinal design with robust MRI techniques.
tom_hartke
1 replies
1d22h

It's worth highlighting that first result is exactly what you asked for, given all 4 of your criteria:

1. It's on adults.

2. It's longitudinal over multiple years.

3. It studies variations in brain volume.

4. It focuses on healthy individuals.

You can see the full results for that search text here: https://undermind.ai/query_app/display_one_search/e1a3805d35...

robwwilliams
0 replies
1d18h

And that first hit in JAMA Open is a fabulous paper. Ten or mire yearly MRI scans for 650 subjects.

redeux
2 replies
2d1h

I’ve been using a similar platform that I really like called Answer This[1]. I’ll have to check out yours as well and see how it compares.

1. https://answerthis.io/

tom_hartke
0 replies
2d

I ran these two example searches we have on our homepage on AnswerThis: (3D ion shuttling) https://undermind.ai/query_app/display_one_search/b3767fb7b6... (laser cooling to BEC) https://undermind.ai/query_app/display_one_search/c5f77f862a...

The results from their website aren't sharable, but their lists of references do not seem relevant (ie. they miss the fact that shuttling needs to be in 3D, and the list of experiments for laser cooling to BEC is missing all of the relevant papers).

I think, like other research tools, they're more focused on the summarization/extraction of information, rather than the discovery process (though they are similar to us in the way they say they do multi-stage retrieval and it takes some time).

ayush4921
0 replies
1d15h

AnswerThis founder here. Hang on tight, our next few updates will be instrumental in conversational feedback-based paper searches.

I love all the work that's being done in the field.

Can't wait for science to be faster.

physicsguy
2 replies
1d11h

My first impression is that it’s quite cool, but it should weight things by importance to some degree.

I tried a search on my previous research area (https://www.undermind.ai/query_app/display_one_search/5408b4...) and it missed some key theoretical papers. At the same time, it picked up the three or four papers I’d expected it to find plus a PhD thesis I expected it to find. The results at the top of the list though are very recent and one of them is on something totally different to what I asked it for (“Skyrmion bubbles” != “Skyrmions”). The 7th result is an absolutely core paper, would be the one I’d give to a new PhD student going into this area and the one I’d have expected it to push up to the top of the list.

jramette
1 replies
1d11h

Appreciate the comments. One thing to note: how much compute it takes to "get everything" varies from search to search, and researchers don't always care about that and usually care most about getting a few specifically relevant results, so we start each search with a first pass with a fixed amount of compute. I know there's a lot to absorb on each search page, but if look near the bottom of the summary, Undermind is predicting is has only found about 80% of the papers with the compute dedicated to this search so far. Logged in users on Pro accounts can "extend" the search until it's gotten 90% or more to ensure exhaustiveness. One other thing I'd be curious about is your notion of "importance" here, can you help us define that here? Any ideas for how would say a very smart human assistant who's not intimately familiar with your community's interests be able to pick out paper 7 from the list according to what you mean by importance? Maybe we need a way to communicate to the system that you're interested in pedagogical or seminal works in the field?

Mkengine
0 replies
1d10h

Not OP and I don't know if that would be feasible for you, but a Pro feature could be something like https://asreview.nl to determine importance/relevance?

ziofill
1 replies
1d14h

We’re both physicists, and one of our biggest frustrations during grad school was finding research

You should have seen what it used to be like a few decades ago :)

jramette
0 replies
1d14h

Agreed, it used to be even harder. But on the other hand, there were also way less papers back then to have to sift through :)

xbmcuser
1 replies
1d6h

Something like this was the first thing that came to my mind when chat gpt and their ilk started showing up. The amount of knowledge in so many fields is so vast that it is impossible for any one or even a group people to access and utilise properly. Serendipity is still needed for many things LLM will make it occur more regularly

tom_hartke
0 replies
1d3h

If it's easy/fast to check the literature, hopefully people's instinct changes. If we had time, we should be doing that for any small idea.

winddude
1 replies
1d20h

Curious as to what it's doing under the hood, the query to return the results takes an excruciatingly long time... are you searching remote sources vs a local index?

this was the search <https://www.undermind.ai/query_app/display_one_search/cba773...> if you need a reference too it, ie bugs or performance monitoring...

tom_hartke
0 replies
1d20h

The few minute time delay is primarily because of the sequential LLM processing steps by high quality LLMs, not database access times. The system reads and generates paragraphs about papers, then compares them, and we have to use the highest quality LLMs, so token generation times are perceptible. We repeat many times for accuracy. We find it's impossible to be accurate without GPT-4 level models and the delay.

jramette
0 replies
1d16h

Love it.

thor-rodrigues
1 replies
1d3h

Hi Josh and Tom, thank you for the post.

Are there any plans on releasing any sort of API integration? I work in Technology Transfer consultancy for research institutes in Europe, and often we have to do manual evaluation of publications for novelty check and similar developments. Since most of the projects we work on were developed by leading researchers in academic institutions, it is important for us to quickly assess if a certain topic has been studied already.

Currently, one of my company's internal projects is a LLM-powered software to automate much of the manual search, together with other features related to the industry.

I think it be very beneficial for us to implement academic papers search function, but for that an API system would be required.

Great work nonetheless, good luck on the journey

tom_hartke
0 replies
1d2h

We'd love to talk and see if we can provide this. Seems like it would be really helpful. Can you email us (support@undermind.ai)?

smcsdp
1 replies
1d21h

what are your biggest drawbacks?

tom_hartke
0 replies
1d20h

Latency, compute required, and lack of full texts (paywalled publisher content).

sam1234apter
1 replies
1d22h

How is this different from Scite, Elicit, Consensus, and Scopus AI for Generating Literature Reviews

tom_hartke
0 replies
1d22h

Ours is slow, but accurate, even for complex topics. The rest are fast, but generally can't handle complex topics. (There's more nuanced explanations in other comments)

qxfys
1 replies
1d9h

Tried it. It would save me a lot of time, I would say!

One suggestion: The back-and-forth chat in the beginning could be improved with a more extensive interaction. So, the final prompt could be more fine-grained into a specific area/context/anything one would aim for.

tom_hartke
0 replies
1d3h

Can you be more specific? Like break it out into AND and OR statements? Or just more iteration back and forth? We find people more familiar with the system learn better strategies than the LLM can suggest.

pointlessone
1 replies
2d1h

OK, I'm both impressed and disappointed.

I did 2 searches.

First I asked about a very specific niche thing. I gave me results but none I wanted. It looked like I missed a crucial piece of information.

So I did the second search. I started with the final request it written for the previous search and added the information I though I missed. It gave me virtually the same results with a little sprinkle of what I was actually after.

A few observations:

1. I'm not sure but it seems like it relies too much on citation count. Or maybe citations in papers make it think that the paper is absolutely a must read. I specifically said I'm not interested in what's in that paper and I still got those results.

2. I don't see much dissertations/theses in the result. I know for sure that there a good results for my request in a few dissertations. None of them are in the results.

That said, while I didn't get exactly what I want I've found a few interesting papers even if they're tangential to the actual request.

tom_hartke
0 replies
2d1h

A few possibilities: - We only use abstracts for now. Have to make sure you ask for something present there. - Did you ask for a scientific topic? (Sometimes people ask for papers by a specific author, journal, etc. The system isn't engineered to efficiently find that).

Regarding citations: we use them, but only for figuring out which papers to look at next in the iterative discovery process, not for choosing what to rank higher or lower at the end (unless you explicitly ask for citations). It's ranking based on topic match.

If you're comfortable, posting the report URLs here can let us debug.

phren0logy
1 replies
2d2h

I have only tried one search, but so far it's impressive. I have been using elicit.com, but they seem to be taking a different approach that is less AI-heavy. I would definitely give this a shot for a few months.

tom_hartke
0 replies
2d2h

We're trying to bias the system toward more autonomous execution, rather than a "copilot"-like experience where you iterate back and forth with the system. That lets us run more useful subroutines in parallel in the backend, as long as you specified your complex goal clearly.

minznerjosh
1 replies
1d23h

Are you planning to offer a search API at some point?

tom_hartke
0 replies
1d23h

Potentially. Given the latency and the cost/compute we put into each result, it doesn't fit the usual API mechanics.

What use case are you thinking of?

mangoparrot
1 replies
1d20h

would this be able to find the latest articles on a given topic?

let’s say i am interested in coffee and i’d like to get new research papers on it. would this work?

tom_hartke
0 replies
1d20h

In short, yes, though it's geared toward topic search.

From a strategy perspective, we designed it for topic search because it makes more sense to find everything on a topic first, then filter for the most recent, if recent is what you want. That's because there is a lot of useful information in older articles (citation connections, what people discuss, and how), and gathering all that helps uncover the most relevant results. Conversely if you only ever filtered on articles in the last year, you might discover a few things, but you wouldn't have as much information to adapt to help the search work better.

So, you can ask for articles on coffee (though ideally it should be something a bit more specific, or there will be thousands of results). Our system will carefully find all articles, then you can filter for 2024 articles or look at the timeline.

iandanforth
1 replies
1d16h

"Please use a valid institutional or company email address."

This is obnoxious. Please remove this unnecessary roadblock.

gradschool
1 replies
1d2h

I did a search on an obscure topic I like and got impressively well informed results, so hats off to you. If this isn't an awkward question, how does one avoid running afoul of Google's rules against crawling when implementing a service like this? If someone were to post a link to a report obtained through your service on a blog or something, would that be a good thing in your view or more like piracy?

jramette
0 replies
1d1h

That's awesome! We're just putting publicly available information (abstracts aggregated by the nonprofit Semantic Scholar) through a smarter and better search process, so there's no issues with Google. And we absolutely encourage sharing, people post our search reports and send them to colleagues all the time, so please go ahead on that front.

bobobob420
1 replies
1d4h

Ycombinator has really fallen off

Razvin_Ilia
0 replies
1d2h

why?

Geee
1 replies
1d23h

I've been using https://exa.ai for this. It doesn't do any advanced agent stuff like here, but it's way better than Google, especially if you're not quite sure what you're looking for.

tom_hartke
0 replies
1d23h

Agreed, exa is great - particularly, it's the best thing I've found for fast web retrieval of slightly more complex topics than Perplexity, Google, etc can handle.

8thcross
1 replies
1d17h

is there a way to configure sources used for research? what about ability to search through paywalled journals?

tom_hartke
0 replies
1d17h

Not at the moment -- we're currently searching the abstracts of most major journals (which are public even for paywalled papers) which have been compiled in the Semantic Scholar database (https://www.semanticscholar.org/about/publishers).

timdellinger
0 replies
1d21h

I'll write the obligatory comment about doing literature searches in the 90s, which involved trudging to the physics library, the chemistry library, and the engineering library in search of dead tree copies of the journal articles you're after. Also: skimming each paper quickly after you photocopy it, to see if it references any other papers you should grab while you're at the library.

smcsdp
0 replies
2d

Any idea how i can use your tool for a vs code extension

skyde
0 replies
1d11h

Could not try it. Saying valid institutional or company email address.

It doesn’t recognize my university.

richardreeze
0 replies
1d1h

Great product!

One thing I'd improve is how it asks followup questions.

For example, I asked "What are the best types of videogames that improve cognition?"

The followup response was

```

Are you specifically looking for studies that focus on cognitive improvements as measured by standardized tests, or are you more interested in everyday functional improvements observed in real-world settings?

Could you be more precise about which cognitive domains you're interested in? For example, are you focusing on memory, problem-solving, attention, or something else? Additionally, are you looking for papers that compare different genres of videogames (e.g., action, puzzle, strategy) or studies targeting specific age groups or populations (e.g., children, older adults)?

Lastly, are you interested in experimental studies where the cognitive benefits were directly measured pre- and post-intervention, or are observational studies that report correlations between videogame use and cognitive performance also of interest to you? Understanding this will help determine the type of articles we should prioritize in the search.

```

It would be great if it turned those into multiple choice. For example:

```

Could you be more precise about which cognitive domains you're interested in?

[] memory

[] problem-solving

[] attention

[] something else (please specify)

```

Would save a ton of time having to reply/ reread everything.

mrweiden
0 replies
1d19h

Ref to prior art: https://en.wikipedia.org/wiki/Meta_(academic_company)

One anecdote that I heard from the team developing it: turned out that researchers more readily sourced material from their social networks, notably twitter at the time. Meta's search functionality didn't receive enough traffic and eventually was shut down.

Perhaps LLMs will make the search capability more compelling. I guess we'll see.

kelloggm
0 replies
2d

I'm a CS academic who _should_ be working on finalizing a new submission, so when I saw this on HN I decided to give it a try and see if it could find anything in the literature that I'd missed. Somewhat to my surprise, it did - the top 10 results contained two items that I really ought to have found myself (they're from my own community!), but that I'd missed. There were also some irrelevant results mixed in (and lots of things I was already aware of), but overall I'm very impressed with this and will try it out again in the future. Nice work :)

jspann
0 replies
1d5h

I love the concept and loved the results I got. I tried it out and found a lot of papers both from my lab group and ones related that I had missed. I'd happily pay for it but as a grad student the price is a little steep - would it be possible to make a student tier?

jackmphy10
0 replies
1d1h

This looks really cool! I'm sure I'll be adding this to my toolkit. And I swear by SciSpace Copilot https://typeset.io/ which I've been using for more than a year. It saves my reading time and summarizes the paper extremely well, helps me decode complex topics, automates the literature review, and extracts key findings of the paper within minutes.

iamacyborg
0 replies
1d20h

I’m a marketer rather than a scientist but this proved very useful in helping me find research that’s applicable to my field of work (crm marketing). Nothing particularly new was surfaced but I suppose I wasn’t expecting it to either http://www.undermind.ai/query_app/display_one_search/7140cc6...

i-use-nixos-btw
0 replies
1d2h

Ok, tried searching something incredibly niche, and it came up with results that no search I'd tried through conventional methods could.

There's a 50/50 false positive rate, but I can deal with that. It means looking at 10 papers to find 5 useful ones instead of looking at 1000 papers to also find 5 useful ones.

I'm impressed.

hgarg
0 replies
1d10h

Is this magic?

havkom
0 replies
1d5h

This looks cool!

glitchc
0 replies
2d1h

This is a nice search rngine. I found it to be more effective than crawling with google scholar. Good work guys!

gillesjacobs
0 replies
1d23h

Pretty good, it found some useful references I missed in Google Scholar and Arxiv. Looks promising, will use it more.

cbracketdash
0 replies
1d16h

Been using Undermind for several months now and it's honestly been a lifesaver in getting a comprehensive understanding of a research topic.

benzguo
0 replies
1d19h

This is really cool! Both of my parents are cell biologists, and I've done some time in labs as well, so a lot of paper exploring and reading in the family. "Review" articles are a good index but something more on-demand makes a lot of sense, I can definitely see this being extremely useful.

alexp2021
0 replies
4h11m

Hi, Looks good on first try. You mentioned the tool currently searches abstracts only. Searching full papers appears impossible as they are mostly behind paywalls, right?

admissionsguy
0 replies
1d7h

This works well. Well done. There was a similar product on HN a few weeks ago and it mostly failed on my favourite topics. Undermind returned all the papers I would expect. The ordering of the results could be improved since in the case I tested, it does not reflect well the relative importance of the papers. I think it may give too much weight to direct similarity to the search query, which could sometimes be an advantage.

adi2907
0 replies
1d13h

Very impressed. I am not a scientist but am building a product for intent-based discounting in Shopify. Typically Google scholar gives me very generic results using LSTM etc however this search gave me some interesting results with focus on real world implementation. The clarifying questions are also quite impressive as it gives the impression that it is understanding the query really well. Good stuff. I think it might be useful for end-users and not just company/research folks as well

adalacelove
0 replies
1d10h

Congratulations for an LLM that doesn't give me BS. I'm sending links to colleagues and most probably subscribe myself

Tsarp
0 replies
1d3h

quite impressive! This is really more like what I was hoping Elicit would be.

Are you breakdown the question into subtopics, doing a broad search and then doing some sort of dim reduction -> topical clustering to get it in the format?

SubiculumCode
0 replies
1d12h

Impressive result. I will visit again

KrisGaudel
0 replies
2d2h

This is really cool, excited to see where this goes!

BOOSTERHIDROGEN
0 replies
1d11h

It would be impressive if the pricing were based on the country's income level.

A_D_E_P_T
0 replies
1d5h

I've just tried it and it looks good. Will probably sign up.

If you can get this to work for patent searches across multiple languages, you'd really have a killer product. Patent searches, via an attorney, cost thousands of dollars each and are nevertheless frequently imperfect. (I had a patent denied because somewhere, in a throwaway paragraph buried in the 100-page description of an entirely different invention, something similar was briefly mentioned and never referred to again.)

I'd gladly pay $100/month for "Deep Patent Search," and more than that if it's really good.

19h
0 replies
14h54m

Absolutely phenomenal quality. Subscribed to the pro plan! Please add an option to use Claude as I absolutely prefer it to GPT4 and it's probably cheaper too.