thallukrish

When complexity increases, you end up handholding them in pieces.

Yes. That seems to be the case. While it may not be saving any time compared to generating general python code vs. specific symbolic code, the real value could be that it has an engine to enforce the contract on LLM responses with the library or even do the calls to the LLM as a common piece of code making it less error prone and bringing consistency in the interactions with the LLM.

Since code is generated by LLM these days, how does specific syntactic constructs like a Symbol which essentially carries the context and can be manipulated with python operators help when compared to a normal python code generated by LLM with all the checks and balances instructed by a human? For example, I can write in this syntax to convert all fruits to vegetables or I can simply prompt an LLM to construct a program that takes a list of fruits and calls a LLM in the background to return the vegetables equivalent. I am trying to understand the difference.

The problem with organizing is not the lack of tools or techniques. It is simply not possible to devise a system which works automatically with little effort. Everything requires varying levels of discipline which is hard to keep up with time and a different situation.

this is like minecraft.

Don't find time for something. Find something that takes your time.

Will it give the same answer for a question or change the answers every time you ask it ? Just curious.

Humans seem to do a million different things. And all of them were kids growing into adults and do by learning to do things. Isn't that good enough if a machine did just that - ready to learn if taught, to be classified as being generally intelligent ?

What if unique content is not the one I want?

I've been a dev building things and I can resonate with what you say very much. A builder is like someone who has a hammer in his hand with everything around looking like a nail. Esp. if you are a builder who is constantly excited with your own ideas, it's hard to ask who would want that ?

There is no perfect answer for a query. There can only be contextually meaningful answers. They can be from highly relevant to far off. It is very hard to prove a search engine as bad in general. It may not work for you. But it may still work for a lot more. Google has indexed the entire Web. This is as large a span as one can take.

Wrote this during the lockdown.

https://thallukrish.medium.com/noise-and-well-being-a9f0b30d...

Actually the place does not matter if you have dreams bigger than the place. Pursue them wherever it makes sense. If your dream is to build a startup go build it. If it should be done in India or Timbuktoo, go do it there. Just because you stay in the US or Europe, doesn't mean you can have better dreams. You may be among those who are able to dream better. It may give you better clues as to how to dream compared to India. But hey, in a flat world, you can dream sitting anywhere and go for it wherever you are. It may be a bit harder to do things in India. But without a doubt, the number of problems you can solve in India is far greater than developed countries. In that sense, if you are done with all the Education and stuff and you are reasonably good on finances, India is a lot cheaper to sit and dream and make things happen.

Unless you are outright promoting commercial stuff, I feel for writers who are relatively unknown and would like to get feedback on what they write, HN is a good place to post links.

This is not different from posting interesting links you find. It is not self-promotion as you are not selling anything here. Instead you are trying to see if the content resonates with others and kickstarts a discussion.

In fact, I see it as no different from the comments we are writing here.

The more you think about enlightenment, the more you are away from it.

oh you are spot on with your feelings. And you can do nothing about it. You will figure out however something that will work for you and move on with life. I could've told this and that. But I just want to be honest.

Why can't they give laptops and internet connection free to kids and get them going online until this settles down?

What is so difficult about this ?

People don't know what to do with their time. For those who know, they don't know why they do, what they do.

Anything competitive is useless

You can't express this feeling better than this. Oh! what a relief that someone could state the problem.

There are 1000s of SHOW HN. But a fraction of them get attention. So does that mean the idea was worthless and the person went ahead spending time building it? No, the person who builds always finds it fascinating. It may not become a hit. But you can't say the idea is worthless. It is a lottery. Only few make it. The magic is about doing the best you can on the idea you like and leave it to the audience to decide just like a Movie.

I can give a philosophical answer rather than a technical one. Our lives are filled with learning various things. And we all realize there is no end to it. But truly what makes you feel better about what you do is not this endless learning. It is when you can drop what you learnt and think freely about a problem that you can solve. Until you reach there, you are in a boat tossed by the waves trying to grab whatever you can to keep yourself afloat. Please disregard this answer if it is not of any help.

that's an illusion we carry about us and about others.

Explain your point.

I write a lot of notes in a notebook with pen. But I never see them. Very rarely I may revisit something. And I have often found that even if I read them they don't seem to matter to me now. So is all the hype of taking notes justified I wonder?

the fact that it answers questions like Q: Who was president of the United States in 1955? accurately itself will tell that it is an AI. I guess the whole idea that an AI shouldn't be different from a human to say that it is generally intelligent implies, the AI has to fake its answers to behave like a human. And this means it is not something a desirable trait for an AI as we have enough real humans who can easily sound more human than an AI.

The article does not seem to address, should one patent a method or algorithm that defines your product as a startup before launching the product?

Whatever you described (looking up key signature etc. in youtube) is the real thing. You are trying to do sight-singing and you are working on it. And if you keep at it and get to sing the whole piece,then you have truly achieved your goal. But if you languish on watching more and more youtube videos, say watch how someone else plays a piano piece or go into something inconsequential to the original problem in hand, then in your mind you started with something and you have not done enough to help that. I am not exactly telling that sidetracking is the problem here, but you moving farther away and away from the original set aside goal is what I am saying.

A bunch of servers on the cloud.

probably you can have a ML program that generates variable names, given the situation in the code.