Thanks so much for your work. I moved to emacs to have a better integration between cli and the editor I am using and ghostel is a tremendous improvement over vterm.
I like to use them to generate me tutorial series for technical topics I want to learn or improve. So I start a prompt like this:
> I want you to create a tutorial series about X for me. The prime objective is that I improve in topic X so never provide a solution but guide and teach. (for programming never write code).
First create a question catalog to assess my current level.
Then I would ask it to structure the tutorial challenges in the following way:
- Goal
- Concept
- Instructions
I figured that if I don't need to read any additional material on the topic the LLM is giving me too much information and I need to change the prompt.
Works for me and I used this too learn topics I feel now comfortable with, like nushell, opencyper, elisp, boot loaders etc.
But maybe you don't consider this "complex"
Curious: Why not pick up a book or two on the topic, and use the LLM to help you through it [0]? To me, prompting the LLM without grounding it sounds like a sure shot way to end up learning "pop-sci", as GP puts it, instead of the actual science?
If today's top LLMs are reliable enough (without grounding) to academically learn "complex topics" from, may be I need to adjust my priors. I must say, I do find myself chatting about other topics (without the need for grounding) that I'm trying to "absorb" (not really learn), like Behavioural Psychology & Philosophy.
[0] Products like NotebookLM are built specifically for such usecases.
I use books to accompany my learning, but I really need something that _forces_ me to think and solve problems in that space on my own.
Books can sometimes give me the illusion of learning something, but then, when needed, I've notice that I haven't really learned it.
LLMs give me structure based on my current skill level. And basically always I accompany this with books, I love reading. It's a nice combination for me.
I would love to see the "depth" of your knowledge in those topics.
You literally proved the OP's point ... thinking you're learning. More like scratching the surface, with lots of invalid data while not being able to recognize what's invalid.
It's like with latest vector of attacks being spamming Github with malware injected in proper looking code in hope of AI to index it.
Then you paste the code because you don't understand it, but you take it as working and only doing what you've asked for.
This feels like an impossible assessment - yes, a model probably can't give you the education that a advanced/expert book on a topic will, but implying that having a verifiable goal is somehow fake learning feels like an intractable problem.
What level of evidence would be sufficient for you to accept that a model may be able to teach a concept?
I'm happy to take on this challenge with a topic of your choosing, but I don't believe there will be an evidence base that satisfies you that the knowledge is earned or deep enough.
I really wonder where this assessment is coming from? It's not that I use LLM written code for something (in those exercises at least), in fact I don't let the LLM write code (see my prompt example).
It's about guiding me in _doing_ exercises so I learn and I can evaluate if I learned something if I can apply the learning myself.
> It's like with latest vector of attacks being spamming Github with malware injected in proper looking code in hope of AI to index it.
First of all "malware" which is often technology working as intended happens at the OS level, not the github repo level. You can't say a repo is malware in most cases - it depends on the deployment. Second and more importantly, the vast majority of training data would have to reflect the "injected attack" for it to have any bearing.
There are ~30 keywords in JavaScript, compared to 100s of thousands in spoken/written languages.
You cannot "attack" anyone or anything through an LLM. It's an offline, read-only model of text, that's it.
You would hire someone with the expactation that they learn, but you also need to pay them. New hires always slow the team down. And currently you wouldn't even get much out of them, as you can delegate those tasks to AI.
Additionally you can not even be sure that the junior will learn or just throw stuff at AI. The amount of vibecoded Code I have to review at the moment from Seniors is stunning.
So yeah, the market needs Seniors, but there is basically no incentive for a company to hire a Junior at the moment. It's just easier and cheaper to pay a bit better than the market and hire Seniors then to train a Junior for years.
Is there a good resource on how to get better at python prototyping?
The typing system makes it somewhat slow for me and I am faster prototyping in Go then in Python, despite that I am writing more Python code. And yes I use type annotations everywhere, ideally even using pydantic.
I tend to use it a lot for data analytics and exploration but I do this now in nushell which holds up very well for this kind of tasks.
When I'm receiving some random JSON from an API, it's so much easier to drop into a Python REPL and just wander around the structure and figure out what's where. I don't need to have a defined struct with annotations for the data to parse it like in Go.
In the first phase I don't bother with any linters or type annotations, I just need the skeleton of something that works end to end. A proof of concept if you will.
Then it's just iterating with Python, figuring out what comes in and what goes out and finalising the format.
At the moment it is the other way around. LLMs rarely write good code if not instructed by someone that knows what they are doing.
And even then the code is rarely good.
