LovelyButterfly

Yeah, great. Let me tell the hospital whose MRI needs maintenance to just not buy whatever it needs. Wome will die but that's a sacrifice I'm willing to make, right?

Consumer market is not you and your console only.

I've been struggling a lot to understand this ever since the agents thing entered the hype. If I follow a path of requirements, it always comes down to: But why you'll leave the decision to a stochastic tool, when you should a have deterministic approach?

It's software god damn it... the reason why people moved from analog to digital is because you can repetitively execute functions that do always the same thing and it's 0 when it's 0, 1 when its 1.

All the sudden everyone is ok on burning trees to have their cool probabilistic tool named agent to do: maybe it's 0, but it can also be 1, let me "think"... ah yes, for sure it's 2.

The sad part for me is that management people have their heads so much into this hype, that no attack on privacy matters (almost none actually ever did, I know). Only when they suffer a huge blow in terms of revenue or reputation is that they maybe, maaaybe, find will want to listen again the experts.

What you mean? They're right. The content creator has to interact with Gemini to summarise the comments and only then a message would show which could contain a link, to the content creator.

The comment's author has no way of extract data from the content creator just by being leaving a comment. They content creator has click a link that the summarisation shown (likely removed by Youtube because it already doesn't allow clickable links in comments).

Yeah that makes sense. I'm a Master's student myself, ironically on Artificial Intelligence. Often I feel overwhelmed by the amount of papers and the mysterious math logic I have to understand when presented with a model.

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.

As a professor, what's you opinion regard the Socratic method with LLMs? Would that be preferable over simply "give me the answer" prompt?

> This is the "Claude Code" part, or even the ChatGPT (web interface/app) part. Large context window full of relevant context. Auto-summarization of memories and inclusion in context. Tool calling. Web searching.

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.

Most, if not all, commercially available AI models are doing offline learning. The cognition is a skill that is only possible on online learning which is the autonomous part the authors refer to, that is, learning by observing, interacting.

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.

In another two examples:

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.

What led you to believe this is an AI written article?