331–340 of 382 posts
This article has some serious usage of either bad prompting, or terrible models, or they’re referencing the past with their stories. I have experience AI’s deleting things they shouldn’t but not since like, the gpt4 days. But that put aside, I don’t agree with the premise. It doesn’t make the hard parts harder, if you ACTUALLY spend half the time you’d have ORIGINALLY spent on the hard problem carefully building cont…
garbage in, garbage out
I don't think it makes any part harder. What it does do is expose what people have ignored their whole career: the hard part. The last 15 years of software development has been 'human vibe coding'; copy+pasting snippets from SO without understanding them, no planning, constant rearchitecting, shipping code to prod as long as it runs on your laptop. Now that the AI is doing it, suddenly people want to plan their work…
Earlier quoted context omitted.
That doesn't make any sense to me. When the code is written, it's all laid out nicely for the reader to understand quickly and verify. Everything is pre-organized, just for you the reader. But in order to write the code, you might have to try 4 different top-level approaches until you figure out the one that works, try integrating with a function from 3 different packages until you find the one that works properly, h…
> But in order to write the code, you might have to try 4 different top-level approaches until you figure out the one that works , try integrating with a function from 3 different packages until you find the one that works properly If you haven’t spent the time to try the different approaches yourself, tried the different packages etc., you can’t really judge if the code you’re reading is really the appropriate thing…
There is a mathematical principle that verification of a proof is easier than any proof. The same is true in code.
Earlier quoted context omitted.
Because to verify something is correct you have to understand the what makes it correct which is 99% of writing the code in the first place.
That doesn't make any sense to me. When the code is written, it's all laid out nicely for the reader to understand quickly and verify. Everything is pre-organized, just for you the reader. But in order to write the code, you might have to try 4 different top-level approaches until you figure out the one that works, try integrating with a function from 3 different packages until you find the one that works properly, h…
> Reading and understanding other people's code is much harder than writing code. I keep seeing this sentiment repeated in discussions around LLM coding, and I'm baffled by it. For the kind of function that takes me a morning to research and write, it takes me probably 10 or 15 minutes to read and review. It's obviously easier to verify something is correct than come up with the correct thing in the first place. And…
Because to verify something is correct you have to understand the what makes it correct which is 99% of writing the code in the first place.
I'm feeling people are using AI in the wrong way. Current LLM is best used to generate a string of text that's most statically likely to form a sentence together, so from user's perspective, it's most useful as an alternative to manual search engine to allow user to find quick answers to a simple question, such as "how much soda is needed for baking X unit of Y bread", or "how to print 'Hello World' in a 10 times in…
>I'm feeling people are using AI in the wrong way. I think people struggle to comprehend the mechanisms that lets them talk to computers as if they were human. So far in computing, we have always been able to trace the red string back to the origin, deterministically. LLM's break that, and we, especially us programmers, have a hard time with it. We want to say "it's just statistics", but there is no intuitive way to…
Earlier quoted context omitted.
What does "usable" mean? Today's best open source or open weight model is how many months behind the curve of closed models? Was every LLM unusable for coding at that point in time?
By “usable”, I mean “there is a website where I can sign up and chat with the model”.
Earlier quoted context omitted.
People rarely post proprietary code to GitHub. Most of it is open licenses that generally only require attribution. Some use a copy left license. Software patents are not copyright in anyway they are a completely different thing. So this isn't AI getting back at the big guys it is AI using open source code you could have used if you just followed the simple license. Copyright in regards to software is effectively "if…
A great many companies publish proprietary code to GitHub private repos. That is how GitHub makes money.
Earlier quoted context omitted.
> I know this is an anecdote, but try to break down the problem you have in simpler terms This should be the first thing you try. Something to keep in mind is that AI is just a tool for munging long strings of text. It's not really intelligent and it doesn't have a crystal ball.
To add on to this, I see many complaints that "[AI] produced garbage code that doesn't solve the problem" yet I have never seen someone say "I set up a verification system where code that passes the tests and criteria and code that does not is identified as follows" and then say the same thing after. To me it reads like saying "I typed pseudocode into a JS file and it didn't compile , JS is junk". If people learn to…
Earlier quoted context omitted.
In a way it shows how poorly we have done over the years in general as programmers in making solved problems easily accessible instead of constantly reinventing the wheel. I don't know if AI is coming up with anything really novel (yet) but it's certainly a nice database of solved problems. I just hope we don't all start relying on current[1] AI so much that we lose the ability to solve novel problems ourselves. [1]…
> In a way it shows how poorly we have done over the years in general as programmers in making solved problems easily accessible instead of constantly reinventing the wheel. I just don't think there was a great way to make solved problems accessible before LLMs. I mean, these things were on github already, and still got reimplemented over and over again. Even high traffic libraries that solve some super common proble…