mav3ri3k

Excellent read. This consolidated and catalyzed my my spurious thoughts around personal information management. The input is generally markdown/pdf but over time highly useless for a single person. Thete would be value if it is passed through such a system over time.

No, english is my second language.

I had already established from previous chat that upon asking for server.c file, llm's answer was working correctly. Rest of the sentence is just me asking it to use and not use certain header files which it uses by default when you ask it to generate server.c file.Thats because from docs of <sys/socket.h>, I thought it had all relevant bindings for the socket programming to work correctly.

I would say, the sentence logically makes sense.

Yes. This is funny when I know what is happening and I can "guide" the LLM to the right answer. I feel that is the only correct way to use LLMs and it is very productive. However, for learning, I don't know how anyone can rely on then when we know this happens.

There is no easy way to share. I copied them in google docs: https://docs.google.com/document/d/1GidKFVgySgLUGlcDSnNMfMIu...

One with ChatGPT about dbms questions and one with claude about socket programming.

Looking back are some questions a little stupid ? Yes. But affcourse they are! I am coming with zero knowledge trying to learn how the socket programming is happening here ? Which functions are begin pulled from which header files, etc.

In the end I just followed along with a random youtube video. When you say, you can get LLM to do anything, I agree. Now that I know how socket programming is happening, for next question in assignment about writing code for crc with socket programming, I asked it to generate code for socket programming, made the necessary changes, asked it generate seperate function for crc, integrated it manually and voila, assignment done.

But this is the execution phase, when I have the domain knowledge. During learning when the user asks stupid questions and the LLM's answer keep getting stupider, then using them is not practical.

A current 3rd year college student here. I really want LLMs to help me in learning but the success rate is 0.

They often can not generate relatively trivial code When they do, they can not explain that code. For example, I was trying to learn socket programing in C. Claude generated the code, but when I stared asking about stuff, it regressed hard. Also, often the code is more complex than it needs to be. When learning a topic, I want that topic, not the most common relevant code with all the spagheti used on github.

For other subjects, like dbms, computer network, when asking about concepts, you better double check, because they still make stuff up. I asked ChatGPT to solve prev year question for dbms, and it gave a long, answer which looked good on surface. But when I actually read through because I need to understand what it is doing, there were glaring flaws. When I point them out, it makes other mistakes.

So, LLMs struggle to generate concise to the point code. They can not explain that code. They regularly make stuff up. This is after trying Claude, ChatGPT and Gemini with their paid versions in various capacities.

My bottom line is, I should NEVER use a LLM to learn. There is no fine line here. I have tried again and again because tech bros keep preaching about sparks of AGI, making startup with 0 coding skills. They are either fools or genius.

LLMs are useful strictly if you already know what you are doing. That's when your productivity gains are achieved.

I am sorry. I really don't see your point. Typescript is in a completely different league of languages than rust/c/c++ with vastly different use cases.

Also, the world still mostly speaks C99 when iterative improvements are constantly being made up to C23.

From my perspective (college student), it is true that there is godly amount of C code in the world which would remain true for a long long time. In similar sense there are also quite a lot of new java developers who maintain the millions of lines of java code.

However a lot of new infrastructure is being developed in rust. Infact it can be argued that the very reason it should be in rust is because it is critical. I think there would be great value if a person can efficiently thread between both rust and c rather than competing.

Fair enough. I have personally experienced pain with phantoms.

But then what would you advice to do ? There are nightmare patterns in rust and c++. Looks to me as pick your poison just that one is new and other has been around for fair bit.

You examples seems to be for a dynamic environment where things are changing. Rust is naturally at slight odds in such a scenario

Instead of quick and dirty, it allows to embed the logic in the type system such that the compiler can help you. Getting off the ground is much harder but staying there is easier.

.

It is great that the ecosystem is growing, but there is still time for things to trickle down.

As college student I have invested time into rust because I see value in the language but there are absolutely zero entry level jobs or internships. To get my foot in, my only real options are C/C++.

Although in rust, function like macros make it super hard to trace code. I like them when I am writing the code and hate then when I have to read others macros.

The first piped query language I used was Nushell's implementation of wide-column tables. PRQL offers almost similar approach which I have loved dearly. It also maps to different SQL dialects. There is also proposal to work on type system: https://github.com/PRQL/prql/issues/381.

Google has now proposed a syntax inspired by these approaches. However, I am afraid how well it would be adopted. As someone new to SQL, nearly every DB seem to provide its own SQL dialect which becomes cumbersome very quickly.

Whereas PRQL feels something like Apache Arrow which can map to other dialects.

I have more and more experienced, best aggregators are people. I really wish For You pages can get to that level.

I did not know that Orcas were endangered up until now. Seems like this approach is working for raising awareness.

I am not deep into llms so I ask this. From my understanding, their last model was open source but it was in a way that you can use them but the inner working were "hidden"/not transparent.

With the new model, I am seeing alot of how open source they are and can be build upon. Is it now completely open source or similar to their last models ?

Using theory of patches would better compliment the current approach. Integrating a scm such as https://pijul.org or atleast the underlying tech would allow for better conflict resolutions. Transferring patches should also allow for more efficient use of io.

Fair enough. I went through qr code of my previous metro ticket to see what info they encode. It is non standard so there were - some hashes - type of ticket, in my case single use, - time of issue, - valid upto time, approx 10hrs, approx journey time was only 30 min - ticket id - I could not directly see source/destination address, but it is my hunch that atleast the destination address is encoded

Now this one time ticket needs to generated before entering the metro station and the qr code is scanned at * both entry and exit*.

I think the entire system works on daily rotating ticket id validated using unique hashes where a ticket validity period is tracked. I think this should be enough to ensure non-reuse of same ticket.

The caveat is, I have always only bough one time ticket which is the only mode allowed in qr. For daily traveller's, they need to buy token/card which is NFC based.

I am not sure which part is impractical. In India we already use QR code for metro tickets. The system design is definitely different from one mentioned and mimics more of how airport tickets work.

Really excited about semantic index. This should allow for google knowledge graph like features grounded in reality for their llm. However it really depends how well it works.

My entire post very was poorly structured. Properly conveying experiences is hard in text, my bad. Just be cautious when you see big scary numbers.

I read through the article. Let me share a small story. I recently completed course for Global Warming in College. I would say my instructor was a quite good. He gave the vibe more of a person in industry who taught than a teacher who published papers. Naturally in course of Global Warming we had figures about how much the globe is warming. We have already raised average temperature by few degree. Current goal of global climate organization is to limit any further increase to 1.5 C and at max, at most dire 2 C. Changes to climate are already somewhat irreversible. So this figure of 1.5 is very sensitive and important. Now this is all good but who decides these numbers ? Who is going to take initiative to meet goals ? Who's fault it was to reach these numbers ?

Moral: These are very loaded figures. Enough to make small naive children make protests and the world to notice. The numbers are very diluted based on agenda. Cancer patients might have increased, seems very plausible. But did the study account population increase or simply number of people reporting ? I don't think so. We all want to make world a better place but take these numbers with a grain of salt.

> “We have adapted our personalization algorithms to this new scenario in such a way that now 75% of what people watch is from some sort of recommendation,” says Netflix

I am always sceptical of these claims. Today algorithms have become ai models. Sorting algorithms are recommendation engines.