• 1 Post
  • 33 Comments
Joined 1 year ago
cake
Cake day: June 24th, 2023

help-circle













  • The paper I linked doesn’t look into all possible aspects because it’s a peer reviewed scientific work, which unlike blog posts tend to have narrow scopes and aren’t written to debunk every aspect of random peoples thoughts on the topic.

    The long and short of this is that people need to be much, much more discerning in which information to trust and which to disregard. The author of your article had a Ph.D. , they could seek to publish their research in serious journals, but they’d need to actually do the hard work of finding reliable, evidence based , peer reviewed sources to do that. Instead we get a blog post the links out to other blog posts that link to yet more blogs, occasional draft papers, and decidedly non scientific works.

    If I were to trust this author writing in this medium, why not trust anti-science fossil fuel interests who use the same mediums and communication strategies?

    Are you familiar with the concept “the medium is the message”?
    For me, it’s a big no thanks, especially on important issues like the adoption of BEVs.





  • I’ve been using the new GPT feature of ChatGPT to improve my own feedback on student work. If you don’t know, GPT is like a customized, purpose driven ChatBOT. So I set one up with the purpose of evaluating my feedback and recommending ways to improve it. I can provide the GPT with ‘knowledge’ about a topic in the form of word files and PDFs , then as I grade I simply give it my feedback and instantly receive suggestions for improved feedback that are based on my original feedback and the knowledge base.

    It’s flawed, and occasionally messes up, but more often than not it improves the quality of feedback a great deal, expanding a 2-3 sentence piece of critical feedback into a 2-3 paragraph piece of critical evaluation, references to the knowledge base and relevant examples of why the students should take the advice.

    Anyway, this relates back to the article with the concept of RAG (result augmented generation) , I give the GPT knowledge to work from, and I have found that it still gets it quite wrong, quite often, especially in some use cases. For example, I generated a GPT for creating quiz questions from a knowledge base, and it was wrong more often than the feedback GPT. The feedback GPT is , as this article says, brittle. If I give it multiple students work, or pieces of feedback, it will start confusing them very quickly. Which is notnideal since you want feedback to be customized per student. Once I realized that, it was solvable by simply starting a new instance of the GPT. But any instructors not paying close attention would see feedback meant for one student end up on anothers paper.