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

Biomni: A General-Purpose Biomedical AI Agent

github.com

Post reply on HN
Print view View original

21–30 of 43 posts

Re: Biomni: A General-Purpose Biomedical AI Agent

#21

Post by mrlongroots »

lawlessone wrote: post #11
mrlongroots wrote: post #10

Earlier quoted context omitted.

Exactly. To present a potential usecase: there's a ridiculous and massive backlog in the Indian judicial system. LLMs can be let loose on the entire workflow: triage cases (simple, complicated, intractable, grouped by legal principles or parties), pull up related caselaw, provide recommendations, throw more LLMs and more reasoning at unclear problems. Now you can't do this with just a desktop and chatgpt, you need a…

>pull up related caselaw Or just make some up...

At the token layer an LLM can make things up, but not as part of a structured pipeline that validates an invariant that all suggestions are valid entities in the database.

Can google search hallucinate webpages?

Re: Biomni: A General-Purpose Biomedical AI Agent

#23

Post by dmezzetti »

Very interesting work!

If biomedical research and paper analysis is of interest to you, I've been working on a set of open source projects that enable RAG over medical literature for a while.

PaperAI: https://github.com/neuml/paperai

PaperETL: https://github.com/neuml/paperetl

There is also this tool that annotates papers inline.

AnnotateAI: https://github.com/neuml/annotateai

Re: Biomni: A General-Purpose Biomedical AI Agent

#24

Post by goda90 »

VerminOctopus1 wrote: post #5

Not to take away from this or its usefulness (not my intent), but it is wild to me how many pieces of software of this type are being developed. We’re seeing endless waves of specialized wrappers around LLM API calls. There’s very little innovation happening beyond specializing around particular niches and invoking LLMs in slightly different ways with carefully directed context and prompts.

Think of it this way: before the internal combustion engine people used animal power, steam power, human power, wind power, etc to move cargo, passengers, and even specialized loads like water pumps for the fire brigade. Then with internal combustion they did those things faster and at greater scale. That wasn't innovating on the ICE itself, or solving new problems. But it was still useful. Of course they also eventually did innovate on the ICE, and they solved new problems with it(heavier than air flight, for example) but it took awhile.

Re: Biomni: A General-Purpose Biomedical AI Agent

#25

Post by ImaCake »

VerminOctopus1 wrote: post #5

Not to take away from this or its usefulness (not my intent), but it is wild to me how many pieces of software of this type are being developed. We’re seeing endless waves of specialized wrappers around LLM API calls. There’s very little innovation happening beyond specializing around particular niches and invoking LLMs in slightly different ways with carefully directed context and prompts.

I suspect it's jumping on the hype train. Especially since its from a big Uni. Funding in research is all about marketing and latching onto the right keywords (just like VC really) so the most successful researchers are those who can market themselves effectively. Whether this tool is actually any good is secondary to whether it achieves the real goal of getting future funding for it's author.

Re: Biomni: A General-Purpose Biomedical AI Agent

#26

Post by tedy1996 »

gronky_ wrote: post #6
VerminOctopus1 wrote: post #5

Not to take away from this or its usefulness (not my intent), but it is wild to me how many pieces of software of this type are being developed. We’re seeing endless waves of specialized wrappers around LLM API calls. There’s very little innovation happening beyond specializing around particular niches and invoking LLMs in slightly different ways with carefully directed context and prompts.

I see it a bit differently - LLMs are an incredible innovation but it’s hard to do anything useful with them without the right wrapper. A good wrapper has deep domain knowledge baked into it, combined with automation and expert use of the LLM. It maybe isn’t super innovative but it’s a bit of an art form and unlocks the utility of the underlying LLM

How is something that cant admit it doesnt know, and hallucinates a good innovation?

Re: Biomni: A General-Purpose Biomedical AI Agent

#27

Post by greazy »

andy99 wrote: post #13

I'm sure they've thought of this but curious how it fared on evaluations for supporting biological threats, ie elevating threat actor capabilities with respect to making biological weapons. I'm personally sceptical that LLMs can currently do this (and it's based on Claude that does test this) but still interesting to see.

Creating a biological weapon requires a whole bunch of unique and specialised skills, equipment, safety measures (so you don't infect/kill yourself/your people) and even multidisciplinary skill sets. Take for example the Kameido (Japan) incident by the Aum Shinrikyo cult/religious group [1]. Same group which committed the Sarin attack [2].

> The use of an attenuated B. anthracis strain, low spore concentrations, ineffective dispersal, a clogged spray device, and inactivation of the spores by sunlight are all likely contributing factors to the lack of human cases.

Now you may say, that's bacteria, what about viruses? A similar set of problems would arise, how do you successfully grow virus to high titers? Even vaccine companies struggle to do this with certain viruses. Then the issue of dispersal, infectivity and mortality arise (too quick, it kills the host without spreading and authorities will notice, too slow, same problem: authorities will notice). I haven't even mentioned biological engineering which requires years of technical knowledge and laboratory experience combined with a intimate knowledge of the organism you're working with.

What worries me the most is nature springing a new influenza subtype. Our farming practices, especially in developing countries, is bound to breed a new subtype. It happened in 2009 (H1N1pdm) and it is bound to happen again. We got lucky with H1N1pdm.

1. https://pmc.ncbi.nlm.nih.gov/articles/PMC3322761/ 2. https://en.wikipedia.org/wiki/Tokyo_subway_sarin_attack

Re: Biomni: A General-Purpose Biomedical AI Agent

#28

Post by panabee »

freedomben wrote: post #2

Awesome! This is the type of stuff I'm most excited about with AI - improvements to medical research and capabilities. AI can be awesome at identifying patterns in data that humans can't, and there has to be troves of data out there full of patterns that we aren't catching. Of course there's also the possibility of engineering new drugs/treatments and things, which is also super exciting.

Agreed. There is deep potential for ML in healthcare. We need more contributors advancing research in this space. One opportunity as people look around: many priors merit reconsideration.

For instance, genomic data that may seem identical may not actually be identical. In classic biological representations (FASTA), canonical cytosine and methylated cytosine are both collapsed into the letter "C" even though differences may spur differential gene expression.

What's the optimal tokenization algorithm and architecture for genomic models? How about protein binding prediction? Unclear!

There are so many open questions in biomedical ML.

The openness-impact ratio is arguably as high in biomedicine as anywhere else: if you help answer some of these questions, you could save lives.

Hopefully, awesome frameworks like this lower barriers and attract more people.

Re: Biomni: A General-Purpose Biomedical AI Agent

#29

Post by knowaveragejoe »

tedy1996 wrote: post #26
gronky_ wrote: post #6

Earlier quoted context omitted.

I see it a bit differently - LLMs are an incredible innovation but it’s hard to do anything useful with them without the right wrapper. A good wrapper has deep domain knowledge baked into it, combined with automation and expert use of the LLM. It maybe isn’t super innovative but it’s a bit of an art form and unlocks the utility of the underlying LLM

How is something that cant admit it doesnt know, and hallucinates a good innovation?

Modern LLMs frequently do state that they "don't know", for what it's worth. Like everything, it highly depends on the question.
Post reply on HN