Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

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

news.ycombinator.com

Post reply on HN
Print view View original

101–110 of 134 posts

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

#101

Post by DonsDiscountGas »

fullstackchris wrote: post #96
passwordoops wrote: post #93

"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

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

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.

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

#102

Post by A_D_E_P_T »

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.

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

#103

Post by passwordoops »

fullstackchris wrote: post #96
passwordoops wrote: post #93

"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

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

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

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

#105

Post by jspann »

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?

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

#106

Post by IanCal »

tom_hartke wrote: post #72
zwaps wrote: post #71

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.

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).

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

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

#108

Post by jpmattia »

passwordoops wrote: post #93

"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

> "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.

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

#109

Post by llm_trw »

passwordoops wrote: post #103
fullstackchris wrote: post #96

Earlier quoted context omitted.

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

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 usual…

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.

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

#110

Post by jpmattia »

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!

Post reply on HN