Accidentally in Google Colab, I've found that there is a "Learn mode" and somehow I managed to access the instructions for it which indeed instructed to ask questions, then I researched a bit more and learned about the socratic method.

So far I'm doing the combo of Zettelkasten + Socratic on Claude on papers + slides or video classes. I'm not sure if it's placebo or not, but I feel much more confident after iterating with each paper or topic this way. Asking the answer to the LLM never felt like I was studying. I read, but I never understood, I was never challenged. Perhaps what we need is the Unis around the globe to come up with a standard, a guideline so that the students can maximise the advantages of having the LLM when a professor or assistant is not available.

From what I've been learning in my uni, this is said pre-programmed. Cognition is really the ability from, out of no context, no knowledge of what you are capable of, to learn something. These tool calling and web searching are, in the end, MCP functions provided by the LLM provider themselves.

It's an entire academic discussion, about how things start. For example babies: they someone have a knowledge base on how to breath, how to cry, but they have absolute no knowledge on how to speak and it learns by the interactions with the parents.

LLMs try as much as they can create this by inference and pre-programmed functions, but they don't have a graph of memories with utility to weight their relevance in the context. As others said, the context window dies as soon as you close the session.

They also don't have the epistemic approach that is to know that another agent knows about something just by observing the environment they were all put in.

In that sense the "autonomous" part you said simply meant that the data source is coming from a different place, but the model itself is not free to explore with a knowledge base to deduce from, but rather infer on what is provided to it.

As a kid, I remember my teachers not allowing us to use calculators and times table pencils exactly to make us go through the painful process of using our brain to get to know math.

Today I'm doing a Master's on AI and AI is a tool I use not only to summarize, but to validate my understading. I don't jump into a GPT session asking it to do the exercise for me or to explain something. I ask it to help me finding out my error after inumerous tries; to say the same thing me in another words because English isn't my first language and often I don't know the terminology that the Academia uses; to write an analogy (which often absurd ones pop up); to guide me where I'm missing something.

It's a freaking powerful learning tool if used properly.