Comment by j_maffe

5 months ago

It redid half of my BSc thesis in less than 30s :|

https://claude.ai/share/ed8a0e55-633f-4056-ba70-772ab5f5a08b

edit: Here's the output figure https://i.imgur.com/0c65Xfk.png

edit 2: Gemini Flash 2 failed miserably https://g.co/gemini/share/10437164edd0

4 comments

j_maffe

Reply
crm9125  5 months ago

Yes usually most of the topics covered in undergraduate studies are well documented and understood and therefore will likely be part of the training data of the AI.

Once you get to graduate studies that's where the material coverage is a little more sparse/niche (though usually still not groundbreaking), and for a PhD. coverage is mostly non-existent since the point is to expand upon current knowledge within the field and many topics are being explored for the first time.

akreal  5 months ago

Could this (or something similar) be found in public access/some libraries?

  • j_maffe  5 months ago

    There is only a single paper that has published a similar derivation but with a critical mistake. To be fair there are many documented examples of how to derive parametric relationships in linkages and can be quite methodical. I think I could get Gemini or 3.5 to do it but not single shot/ultra fast like here.