Galactica: an AI trained on humanity's scientific knowledge (by Meta)

> https://galactica.org/?prompt=lit+review+on+phase+contrast+m...

  Phase Contrast Microscopy, A Survey

  Summarized by Galactica

  Abstract

  Phase contrast microscopy has been developed in the past 20 years into a powerful tool for the study of living cells and other biological specimens. In this article we review the theory of the method, the practical design of phase contrast systems, and the applications of the technique.

I think a good way to think about scientific language models is that they're useful in exactly the same ways general language models are, but in a very narrow domain (stuff having to do with scientific papers & patents, for the most part).

Use-cases that are possible/useful today:

- Annotation of scientific texts: is this paper about computer science?

- Scientific search: please give me researchers or papers most similar to an input query.

- Helping PhD Students graduate (only kind of kidding)

Use-cases I think will be possible/useful in the forseeable future:

- Scientific question answering: e.g. ask the model to explain a chemical process

- Scientific advice or guidance: e.g. ask what method might be appropriate in a situation.

- Text completion/editing/etc: e.g. help me write my paper. You could probably do more of this today if more $ was invested in science models, we're likely ~5 years behind whatever is going on in the "normal" language space.

As far as potential / shortcomings I'm really pessimistic. I don't think large language models for science are very useful outside of bespoke projects or ever will be for people doing serious science. The main issue is that these models are way too general - if you have a specific science problem you want to solve, its almost always going to be better to train a model to specifically address that problem. You would never, for example, ask a model like Galactica to do what AlphaFold does. Eventually you might be able to, but its never going to outperform a specific model, so if you're a researcher trying to get the best results why would you use it?

I should also add, scientists really care about precision. When summarizing a news story exact words might not be that big a deal, but if you're trying to summarize a scientific paper getting a word wrong can REALLY matter. The bar these models need to clear before scientists trust them with tasks where precision matters is likely much, much higher than in other domains.

I think the most likely outcome is that ~75% of LLM use for scientific text outside of academic research papers will be for search related products. That's definitely a place where they can make a big difference: help people find and understand cool papers that are relevant to their research.

Space-time continuum documents

It responded with:

Space-time continuum documents (or STC documents) are a form of technical documentation that combines a traditional paper document with an electronic document.

STC documents combine a traditional paper document with an electronic document that is accessible online. This allows the document to be printed and read on paper, but also allows the electronic version to be read online, which may include hyperlinks to other documents.

STC documents are typically created using Microsoft Word. A .docx file is used for the paper version and a .pdf file is used for the electronic version.

>Prove the last digit of pi is 3.

    import math

    def main(): for n in range(1000): x = math.sin(math.pi * n) if x > 0.99: break else: print("error")

    main()