Can you give an example prompt for this approach?

Having only taken one syntax class for fun in college, I find this pretty impressive. Generating syntax trees was never a trivial task for me (but I was just a CS major who needed a credit). Slightly related, but I have also never had ChatGPT successfully generate ASCII art, even with extensive conversation.

If you ask it to draw a dinosaur it does an okay brontosaurs.

                 __
                / _)
       _.----._/ /
      /          /
   __/ (  | (  |
  /__.-'|_|--|_|

Asking for a Tyrannosaurus Rex gives you more or less the same brontosaurs:

                   __
                  / _)
         _.----._/ /
       /          /
   __/ (  | (  |
  /__.-'|_|--|_|

Yeah, I think it would be very challenging for most people. It did considerably better with Graphviz than with ASCII art, but it still had trouble with the transition from a perfectly correct and highly nuanced verbal grammatical analysis to Graphviz. I think this is pretty convincing evidence against ChuckMcM's implicit position. It's weaker evidence against mschuster91's explicit position because parsing is something computers have been doing for a long time, so it doesn't imply any new capabilities.

I'm pretty sure there are part-of-speech tagging parsers using fairly shallow statistics that could also have produced an equivalently good sentence diagram. https://corenlp.run/ seems to produce a correct parse, though in a different format.

Since I graduated college last year and started working full time as a software engineer this year, I’ve been trying to navigate the financial world and set myself up for financial success. I feel like I’ve been able to get into a good place with just reading and napkin math, but this looks like the perfect tool to get away from semi-qualitative to quantitative decisions. Will be checking out!!!!

Glad to hear it! If you see places where you feel there should be more educational scaffolding, just let me know.

This is really neat. I imagine this will be an entryway for LLMs to creep into more classic data science / ML workloads.

The mechanical watch article / walkthrough is one of my favorite finds on HN. Really great design and explanations, both visually and conceptually. I’ve shown it to several people because it’s that cool

Finally, a reason for taking cpsc 323

Watching Blender become more and more prominent over the last several years has been extremely satisfying. This looks like another great step.

finally. I have a wikipedia page to reference when my friends think I'm being stupid lmao