It's much better to feed the book to the LLM and ask questions as you read along, instead of asking the LLM to basically write a custom book for you from scratch.
For example having an LLM summarize a dense topic and to find books so that you can filter faster and spend time reading those books works way better than having the LLM summarize the books or the topic (or even relying on second hand information). Another one is having the LLM quiz you on your topics of interest. With questions tailored to attack specific areas that you struggle with. Its wonderful at this, nothing I've used comes close to what an LLM can do here.
You define for yourself what your goals are, slowly refining them as you learn more, and use LLM as a tool. This ,I find works best for learning.
It's long been the case that the best way to learn something is to teach something.
Which is pretty unfortunate for those that want to learn. I used to enjoy writing documentation at work, it was my favorite part of the job. And it did feel like it benefited me more than it benefited all the people that were (or weren't) reading my documentation. Now I can't really justify spending much time on docmentation when LLM's can do it in a fraction of the time and it's "good enough"
Is it perfect? No. But it suffices most of the time in a pinch.
Can’t speak to the nuke industry, but it’s pretty good at aviation related things.
Then elaborate in small chunks so the human domain expert can remain focused during review.
You tell it what you need, and it pretty much does all the work: > please give me a 135 compliant maintenance manual, use the attached document as a primer, reference every part 135, 91, 43, and 65 reg as appropriate as well as the other included manuals. Make sure to reference every requirement in the attached list of requirements. Aircraft mx manuals are in the folder “mx-manuals” and our current forms are pdfs in the “forms” folder. Remember our operation is <describe scope of operation here>, not a major airline. Have fun!
This does surprisingly well and meets requirements at about 95% or better accuracy. Typically the only problem I routinely is trying to make the manual like a Delta Air Lines manual instead of one for a small air taxi.
This is a great idea. I'm going to try it.
And you notice when it's a topic you know well or something like software where you can immediately tell the options it's giving you don't exist on the page. Leading to the amusing statement "LLMs are bad at what I do but great at everything else".
The question: what's the net positive gain of turning people who know nothing in a given field into sub-novices, while weighing actual experts down with work slop and marginal returns?
And I wonder what the true cost is of arming so many novices with that level of dangerous knowledge.
Tangentially, but related: I'm old enough to remember when the spirit of your comment was pervasive on HN.
I’m old enough that I worked my first IT summer job the same year slashdot was founded. I’ve seen a lot of tech tribalism form and dissipate, and this one didn’t feel organic. My gut says a lot of the us-vs-them tension originated in a deliberate campaign to cast AI boosters as the tech industry in-crowd, and ‘other’ the people not on-board. Who knows.
E.g. the entire framing to combat complaints about shortcomings was, "It's not the tech. It's you. You're just not doing it right. Wrong setup, wrong workflow, add this to your .MD, use loops, etc". Every complaint was immediately met with this same treatment by a swarm of vague bro-bots that materialized from the ether. The core message? Always the human's fault.
And, don't get me started on the waves of newly minted expert AI creators, making recommendations without showing a single example of what they'd supposedly built.
I'm sure some bandwagon organic creators tried to cash in on the genre, but encouraging that was also part of the point.
Just hoping folks don’t get hurt due to people not understanding what they’re doing with these things but believing they’re competent.
Trying to diagrams/animations didn't yield good results even with frontier models. But pure text, any model does a decent job.
So it may be very slow or become unavailable, back end can't handle that, no caching whatsoever.
The body of literature on learning theory, and beyond that on specific types of learning and specific mediums such as learning from text is so rich there are way more useful models to draw from. Believe it or not, prellm, researchers in the textual learning field had already demonstrated you can achieve performance equal or better than novice tutors using pretty basic computer aids that follow specific hint/pump interaction structures. Guiding an LLM to use these findings has evidence backing it and is way better than telling it "i guess be like socrates". The problem is, to realize there might be richer more effective and highly researched ways of tackling the problem beyond the first fart of a thought you had one afternoon requires the deep respect for expertise and specialization that precisely basically everyone in the AI space right now fundamentally lacks.
You need much more time and guidance.
TLDR: Actual human tutoring sessions were recorded and analyzed and Socratic questioning was barely used at all. Instead the following pattern was observed:
Pump — "Uh huh?" "What else?" Costs nothing, so try it first.
Hint — points at the region of the answer. "What about the pumpkin's motion sideways?"
Prompt — fishes for one specific word, with the sentence frame supplied. "The pumpkin keeps moving forward at the same ___?"
Assertion — just says it. "It keeps the runner's horizontal velocity."
This statement would out you as someone who didn't attend an elite school.
I even wonder if this behavior is due to next-token prediction architectures, somehow.
I know you probably don't consider it dense but wondering if someone can shed insight.
I find them like empty calories, like programming youtube tutorials. They maximize for feeling learnt instead of steady progress
It's dense along the wrong axis and verbose Along the wrong axis.
Like having acres of cardboard for dinner: you have too much dinner with not enough nutrition. Your dinner is plentiful and still not enough.
I'd imagine an application that uses LLMs will be created that better manages learning. It's just not clear what that UX is yet- it's obviously not just a chatbot
i run into context window limits, or practical limitations of digitizing the book