LLM Powered Research 馃

Dall-E prompt: A picture of a postcard in the style of sonic the hedgehog showing a researcher having a back and forth discussion on research with an AI agent

All right!  With all that pondering and throat-clearing done (see my previous series of posts), I was wondering what piques my interest in this LLM-hyped world from a practical side. I've been somewhat active in critiquing this whole thing over the past two years, but beyond creating AI images for the blog (or to amuse myself), or using ChatGPT to make silly little genre-busting poems (again amusement and play), and or using ChatGPT to give me a boilerplate letter that I can then tweak (marginal utility, but I guess if organization ask for things that can be boilerplated, they get something that is boilerplate).  I don't mean to dismiss the value of experimentation or play, they are valuable and low-stress ways to get to know a tool and then you may get an AHA!!! moment of a sort. I've been thinking of something more structured. 

I was listening to a relatively recent episode (it was recent when I started writing this darned post!_ of the Vergecast, titled The Chatbot Becomes the Teacher, and I started pondering... I don't like feeding PDFs or other writing into OpenAI's or Anthropic's "ooops, we just used your shit without permission" infrastructure. I also don't want to use open systems that contain a corpus of data that's not pertinent to what I am doing.  I was wondering if setting up my own GPT in a Virtual Machine to run a custom LLM, or using NotebookLM (even though I am not sure where that data ultimately goes) to mess around with my MOOC Eulogy project.  Yes... I have yet to give up on that 馃槀.  I have a lot of PDFs, but I'd like to start fresh with doing a sustained literature collection (articles, books, blogs, youtube videos).  Since NotebookLM can 'digest' all of that, I was thinking that it may be a useful experiment (even though I am bit uncomfortable with not knowing how the proverbial sausage is made).  Since I am pretty familiar with the literature already, having read through most of it over the last 13 years, I am wondering what sort of new "has!" might be gleaned from having all this in a custom-corpus LLM that can be prompted to give some responses.  I suspect that much of what it extrudes will need fact-checking, but I wonder if it's useful as an idea-generation or lead-generation tool. 

Thoughts?馃

Comments

Post a Comment

Popular posts from this blog

Latour: Third Source of Uncertainty - Objects have agency too!

Image
Continuing on my exploration of ANT, and asynchronous and indirect dialogue with Latour - this blog post will cover the third source of uncertainty, which according to Latour, is that Objects have agency too! As with the previous blog posts, I've pulled out quotes from the book that seemed interesting, or that I reacted to in some way, and I am responding to them here. no tie can be said to be durable and made of social stuff (p. 66) This quote seems to continue Latour's assertion that there is no such thing as "social" or "social stuff" and that "social", or the meaning of needs to be negotiated and better understood.  It also continues the thought that social can only be seen from the actions of its actors, the traces they leave behind, and that these bonds are not durable because they need continuous reinforcement. I guess Social is a perishable item. Left to its own devices, a power relationship that mobilizes nothing but social skil
Read more

MOOC participation - open door policy and analytics

The other day I was reading ZML Didaktik on the topic of MOOC participants. In MOOCs, one of the big questions is why are people lurking and not participating? If more than 500 people join a MOOC, why are only 10% contributing with any amount of regularity?  On the same blog, in a previous blog post, I had commented (it was an open stream of thought really) that perhaps there should be an open enrollment period, and then if the system sees that certain participants are bellow a threshold of activity, the system may give them the option to self-identify as a lurker, or un-register from the class. This line of thought went along a view that compared to the traditional classroom; in a traditional classroom students register for the course, they can attend classes for a week and then decide whether or not they want to stay with the course or not. If they do stay with the course they know that there is a certain amount of "lurking" that they can get away with, but they do have
Read more

You've been punk'd! However, that was an educational experience

Image
It's now the end of Teaching Goes Massive: New Skills Required (aka #massiveteaching) on coursera. Well, almost, we still have a couple of days left. I guess that the lesson here is that we were (the "learners") were punk'd† by Paul-Olivier Dehaye of the Univerisity of Zurich. After that last blog post (and subsequent pickup of the post by George Siemens and others) Inside Higher Education and the Chronicle wanted to chat with me about this MOOC experience. I only had time for one of the two before things went to press, so my 15 minutes of fame went to IHE.  Both IHE and the C hronicle have written about the topic, and have received some information from Coursera on the incident.  Others have also written about it (see here , here and here ) It's surprising to me that the University, and Coursera, waited until after this thing was a big issue in order to respond in the class, and clue people into what was happening. On Wednesday (day 3 of Week 3/3 of the
Read more