Generative A.I. arrives in the gene editing world of CRISPR • Hacker News Board

Re: Generative A.I. arrives in the gene editing world of CRISPR

#31

Post by mewpmewp2 » Tue, Apr 23, 2024, 6:42 PM UTC

scarmig wrote: post #25

r2_pilot wrote: post #24

Earlier quoted context omitted.

Computer viruses run on hardware they do not create but merely hijack. Unless a virus took control of a semiconductor fab, it's hard to argue that they are alive/reproducing in the context of this discussion.

Parasites do the same thing: hijack a piece of hardware and use it to reproduce. Computer viruses have even formed a kind of symbiotic ecosystem with blackhats: the scammer provides resources to help the virus reproduce, and the virus provides access to the scammer in turn. In a way, all life hijacks hardware (the material world) that it doesn't create to reproduce itself.

Computer viruses need to get an ability to mutate by themselves, improving the code overtime though.

Re: Generative A.I. arrives in the gene editing world of CRISPR

#32

Post by cjk2 » Tue, Apr 23, 2024, 6:46 PM UTC

m3kw9 wrote: post #30

[flagged]

It cured my investment interest in it.

Re: Generative A.I. arrives in the gene editing world of CRISPR

#33

Post by Mindless2112 » Tue, Apr 23, 2024, 6:48 PM UTC

pointlessone wrote: post #2

What can possibly go wrong if we let ChatGPT edit our DNA?

Have you seen how generative AI thinks hands work? Just a few edits and reality can catch up.

Re: Generative A.I. arrives in the gene editing world of CRISPR

#34

Post by JoeH2 » Tue, Apr 23, 2024, 6:52 PM UTC

mxwsn wrote: post #4

Gift article (no paywall): https://www.nytimes.com/2024/04/22/technology/generative-ai-... Preprint: https://www.biorxiv.org/content/10.1101/2024.04.22.590591v1

Very kind of you! Thank you!

Re: Generative A.I. arrives in the gene editing world of CRISPR

#35

Post by luckman212 » Tue, Apr 23, 2024, 6:52 PM UTC

miraculixx wrote: post #11

Reading their blog post I wonder if an LLMs is really the best way to do this. If I got it right, they used the LLM to enumerate potential protein DNA sequences. Does that really need an LLM? Enumeration is not novel, nor are LLMs particularily good at it. If you want to computationally parallelize the search in a large enumeration space it would be much easier to simply, well, do that instead of taking a detour via…

To be fair, having AI in the title landed it on the front page of HN, so...

Re: Generative A.I. arrives in the gene editing world of CRISPR

#36

Post by meowkit » Tue, Apr 23, 2024, 6:53 PM UTC

miraculixx wrote: post #11

Reading their blog post I wonder if an LLMs is really the best way to do this. If I got it right, they used the LLM to enumerate potential protein DNA sequences. Does that really need an LLM? Enumeration is not novel, nor are LLMs particularily good at it. If you want to computationally parallelize the search in a large enumeration space it would be much easier to simply, well, do that instead of taking a detour via…

The real power of LLMs is they can model anything as a “language” given the right sequence training data.

Warning: the following is my opinion.

In the same way that MLP “neurons” are universal approximators, it seems that LLMs are universal mappers.

They have the potential to help us organize and translate the immense quantity of data being generated by modern methods in all respective disciplines. We might create a model that translates english to protein synthesis, and vice versa, which would be pretty useful given my lay understanding of biochem.

To your point - this probably is NOT the best way to do this in an objective sense. But to my mind we are hitting upper limits as finite beings and need things like this, which utilize native language constructs, to move forward.

Re: Generative A.I. arrives in the gene editing world of CRISPR

#37

Post by yieldcrv » Tue, Apr 23, 2024, 7:00 PM UTC

miraculixx wrote: post #14

genghisjahn wrote: post #12

Earlier quoted context omitted.

Have you seen DNA? Mistakes and dupes and hallucinations all over the place. Ever since Sherlock Crick and Doctor Watson started meddling with it.

It's one thing to analyze it. It's an entirely different thing to let a machine of dubious abilities create new DNA.

machines that undergo accelerate evolution, I would trust them more under rigorous guidelines

I just need to be able to test the guidelines and results. Clinical trial process to make an objective decision from that point.

Re: Generative A.I. arrives in the gene editing world of CRISPR

#38

Post by vessenes » Tue, Apr 23, 2024, 7:02 PM UTC

swamp40 wrote: post #21

Imagine an AI learning from photos/videos of a person and their DNA sequence? And also a list of diseases, health records, etc. Then asking it for predictions while giving it feedback afterwards so it can tune itself. You could even guarantee privacy. That would be some really useful data.

I like this a lot; you could have a multimodal setup with a DNA transformer, an image transformer and an LLM. Extremely fundable startup.

Re: Generative A.I. arrives in the gene editing world of CRISPR

#39

Post by a-r-t » Tue, Apr 23, 2024, 7:02 PM UTC

So the six finger hands were just a foreshadowing?

Re: Generative A.I. arrives in the gene editing world of CRISPR

#40

Post by swamp40 » Tue, Apr 23, 2024, 7:04 PM UTC

paxys wrote: post #23

swamp40 wrote: post #21

Imagine an AI learning from photos/videos of a person and their DNA sequence? And also a list of diseases, health records, etc. Then asking it for predictions while giving it feedback afterwards so it can tune itself. You could even guarantee privacy. That would be some really useful data.

You mean exactly what 23andMe tried to do, and failed miserably at.

We are still early. Eventually you'll be able to change your race, gender, add reptile eyes, regrow limbs etc. Has to start somewhere. Need more data.