[alsodumb]

Depends on what model you're using. I'm a PhD student, I use GPT-4 as a "knowledgeable on all topics but sometimes confidently wrong" companion.

I'd say ChatGPT is where I search first in 90% of the cases these days. I do confirm important things in Google, but the information provided by chatGPT is the starting point of my Google search, especially on topics/questions where I don't have a clear question and a vague idea of what I want - chatGPT gets my thoughts context perfectly almost every single time no matter what the topic is.

[chaxor]

This is a decent way to explain a good use case - exploration of new priors and ideas. For example, I was looking for a good way to do streaming xml parsing in the simplest way possible. One way is to do it via various packages in different languages and write out all the functions to pause etc. Another option (apparently a language, but domain specific) is XSLT. I already knew these things, but by using GPT-4 I found out how to hit a very long list of requirements with just one small XSLTv3 script and a one-liner in bash, as opposed to several hundred lines of python, Julia, or Rust.

Specifically though, GPT pointed me to Xalan (which I had never heard of, and would not have ever seriously considered by looking around for XSLT parsers - because I didn't realize it was the only option for stream parsing xml via XSLT v3. It was able to tell me this a lot more directly and offer why it was the best option to go with for my list of requirements. Even writing python scripts along with XSLT, etc wouldn't make the stream parsing possible because any package available couldn't handle v3.

So yeah, it is quite useful for exploring programming design given a huge list of requirements. But you have to explicitly ask, because it can't read minds and will just choose some design if not specified (it can't read minds).

[d0mine]

To parse xml without loading it into memory, one interesting element at a time in Python:

  import xml.etree.cElementTree as etree

  def getelements(filename_or_file, tag):
    context = iter(etree.iterparse(filename_or_file, events=('start', 'end')))
    _, root = next(context) # get root element
    for event, elem in context:
        if event == 'end' and elem.tag == tag:
            yield elem
            root.clear() # preserve memory

https://stackoverflow.com/questions/7697710/python-running-o...

The usage is simple: getelements() generates the desired elements one by one. Found using google search for "xml memory iterparse"

[chaxor]

Yeah, that's an option I'm aware of, but it gets quite ugly when the rules are more than just a few.

[Paul-Craft]

That's interesting. Are you using it for work in your field of study? What is your field of study if I may ask?

The reason I'm asking is that I studied math in school, and GPT is an absolute garbage fire when it comes to anything mathematical. I could not imagine using it even for graduate level coursework.

[alsodumb]

I broadly work in decision making under uncertainty - so a bit of control theory, a bit of optimization, a bit of machine learning, and AI planning (MDPs, POMDPs).

I definitely don't do math say at the level of a math grad student, but I do fair bit of proofs, mostly using concepts from real analysis and functional analysis. I'd say GPT4 does pretty good sometimes (this is mostly me testing to see how well it works, I don't have a particular use case). I use Github copilot (I believe it uses GPT-3?) to write my latex documents and it works really well at predicting the equations I am writing and saves a lot of time!

[szundi]

I do this when I need “ideas” or “directions” instead of ads and seo optimized bs. Then I can confirm the results with my own research and ping pong between chatgpt and google sometimes.