Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Don't you mean extinct?

fabiensanglard.net

Post reply on HN
Print view View original

71–80 of 145 posts

Re: Don't you mean extinct?

#71

Post by socalgal2 »

overgard wrote: post #58
bitwize wrote: post #27

Earlier quoted context omitted.

No, he is correct. LLMs have much larger working memories for the kind of details you work with in programming tasks. You are at an objective cognitive deficit by not taking advantage of this. Everybody knows what he means by left behind. When you program, you do so with a goal in mind, and you will not be able to reach that goal as quickly without LLMs. You will be outcompeted by those who use them, and this means t…

How many other technologies required death threats for adoption?

This one does not require any death threats. It's a statement of where the world is going. Maybe you disagree. Come back to this thread in 3 year and see which POV was more correct. The

* "LLMs suck, are stupid, I hate them, and I'm not using them"

or

* "LLMs are the future and if you don't adapt you'll left behind"

I'm confident it's this 2nd option. Care to wager?

People might be using hyperbole: "You'll be left behind" = "you'll be out of a job" or "you'll be unemployable" or "You'll die" but they all mean the same thing.

Re: Don't you mean extinct?

#72

Post by konart »

>In 1993, Jurassic Park came out and revolutionized the use of CGI in films

I thought Terminator 2 did this. At least around where I lived everyone talked about T2 and questioned how they did this or that. JP? Not really.

Re: Don't you mean extinct?

#73

Post by alex_suzuki »

overgard wrote: post #14

I think this is a flawed analogy. In the past when we had a new way of doing something that obsoleted the old way, it replaced it because it was an obvious improvement. I mean, stop motion is cool, but obviously there are limitations. The deal GenAI offers is: the result will be mediocre at best, on average it will be slop, but it will do it much faster. Ok, that's a fair value proposition in certain contexts . We've…

My biggest gripe with AI is that I struggle to come up with even one real problem that it has solved in my daily life, and that of my family and friends.

Yes it might have made me a bit faster at some things I do for work. But it seems to me that we face so many challenges as a civilization, and AI doesn’t actively help with any of them? Unless you buy into the narrative that it will somehow usher in a golden age of abundance where everyone is taken care of and nobody needs to work anymore (utter BS in my opinion). The amount of capital flowing into it, that is then not available for other causes, is completely mind-boggling to me.

Re: Don't you mean extinct?

#74

Post by fluoridation »

My_Name wrote: post #55
bryanlarsen wrote: post #6

> I asked an LLM to write a Levenshtein distance function instead of adding a dependency to my project. Which you likely failed to review thoroughly, so may be subtly wrong.

How many dependencies do you review the source code of?

The expectation is that someone has already done that with a dependency. If the code has just been sharted out by an LLM, it has by definition been reviewed or even understood by no one.

Re: Don't you mean extinct?

#75

Post by fabiensanglard »

setheron wrote: post #24

I don't want to curate my own AGENTS file. I'd rather just copy someone else's verbatim similar to code formatting style. Fabien, care to share your whole file? I'll plug it into my NixOS machine.

- Always us {} after if, even on single lines.

- Avoid using magic numbers and strings. There should be consts or even better enums.

- When working on a patch, you should other the test first. Watch the test fail. Then include the new code. And watch the test pass.

- Leverage early return and continue as much as possible to reduce code indentation.

- Only delete comments if they are obsolete. If you change code, make sure the comment above is still correct.

- Use enums instead of boolean for function parameters.

- Talk to me like an engineer. Don't be excessively verbose. Be down to the point.

- Don't use superlative. Stop praising me, give me the cold hard truth.

- Let the reader of the code breath. Add empty lines between logic block of code. Add a small to the point comment to explain what the block does.

- When you write unit tests, add a short comment at the beginning of the function and class to explain what they test and how they test it.

- Check commit message, if you proof read or write one, follow these 7 rules:

Rule 1: Separate the subject line from the body with a single blank line.

Rule 2: Limit the subject line to 50 characters (72 is the absolute hard limit).

Rule 3: Capitalize the first letter of the subject line.

Rule 4: Do not end the subject line with a period.

Rule 5: Use the imperative mood in the subject line (e.g., "Fix bug," "Add feature," not "Fixed" or "Adds"). Test formula: It must complete the sentence: "If applied, this commit will [your subject line here]".

Rule 6: Wrap the body text manually at 72 characters to prevent Git formatting issues.

Rule 7: Use the body to explain what and why vs. how. Assume the code explains the how; the message must explain the context and reasoning.

Re: Don't you mean extinct?

#76

Post by overgard »

socalgal2 wrote: post #71
overgard wrote: post #58

Earlier quoted context omitted.

How many other technologies required death threats for adoption?

This one does not require any death threats. It's a statement of where the world is going. Maybe you disagree. Come back to this thread in 3 year and see which POV was more correct. The * "LLMs suck, are stupid, I hate them, and I'm not using them" or * "LLMs are the future and if you don't adapt you'll left behind" I'm confident it's this 2nd option. Care to wager? People might be using hyperbole: "You'll be left be…

This whole you need to "adapt" to LLMs thing is bonkers to me, because there's practically no skill in using an LLM. It took me a weekend to learn how to use a coding harness, and the skill pretty much generalizes to all coding harnesses. The things that make me potentially good at using a coding harness are my preexisting engineering skills. I'm sorry, but I think if you believe that being on the cutting edge of knowing how to prompt is some sort of magical skill that's going to protect you from economic hardship, you're delusional.

Most of the "cutting edge" stuff I've seen is basically trying to scale the amount of parallel work that can be done, without any consideration to how much that costs, how much waste is generated, or if the output is even useful. Most of my coding time is spent thinking through problems. Which is exactly how I spent my time prior to LLMs.

Re: Don't you mean extinct?

#77

Post by inglor_cz »

marssaxman wrote: post #63
inglor_cz wrote: post #9

Earlier quoted context omitted.

My experience with regard to quality is quite the opposite. With LLM at my disposal, I had the time- and effort-budget to expand test suites considerably, I was even able to attack a somewhat thorny question of reproducible builds on MSVC, which is not exactly friendly towards determinism. These tasks would take me personally so much time that I would have to set them aside, at the cost of output quality.

Likewise - it's not just about generating production code faster; it's now feasible to create all kinds of experiments, test fixtures, visualizers, analyzers, and support software you never would have had time for before, which you can use to improve your process and create a better product. I recently had to evaluate some data one of my coworkers had produced, to decide whether some process was going to be feasible.…

"it's now feasible to create all kinds of experiments, test fixtures, visualizers, analyzers, and support software you never would have had time for before, which you can use to improve your process and create a better product."

Yes, yes, yes, so much yes. Log analyzers, consistency checkers, performance evaluators, all sorts of hooks and helpers, precisely of the "single-use application for a single user - what a luxury!" sort, which made the entire development process so much more secure and comfortable. Most of the tedious moments (looking for a single bad value in a heap of logs etc.) went away.

The scaffolding I have now is a castle. The scaffolding I had a year ago was a log cabin. Nothing against log cabins in general, but castles are a lot harder to break into and have fewer holes for problems to sneak in.

Re: Don't you mean extinct?

#78

Post by amluto »

> Writing tests used to be a pain. This is no longer the case. It is ok to request unit tests/CI tests for each PR. These have never been more important since large refactors are becoming increasingly common. Human and LLM review may miss stuff but good tests should catch breakages.

The default behavior is not necessarily good. You end up with tests that match the code, but you don’t necessarily end up with tests that test the behavior you care about. And then, if the LLM tries to decide whether the code is correct, it can conclude “it matches the test so it must be right” regardless of whether it’s actually right.

TDD can help but is not a panacea.

Re: Don't you mean extinct?

#79

Post by JoeAltmaier »

fabiensanglard wrote: post #75
setheron wrote: post #24

I don't want to curate my own AGENTS file. I'd rather just copy someone else's verbatim similar to code formatting style. Fabien, care to share your whole file? I'll plug it into my NixOS machine.

- Always us {} after if, even on single lines. - Avoid using magic numbers and strings. There should be consts or even better enums. - When working on a patch, you should other the test first. Watch the test fail. Then include the new code. And watch the test pass. - Leverage early return and continue as much as possible to reduce code indentation. - Only delete comments if they are obsolete. If you change code, make…

In comments don't use prepositions (that, it, those) e.g. "It serves those file migration methods". Instead say e.g. "This method is intended to serve methods x,y and z or any method that has set up a migration source and sink".

Re: Don't you mean extinct?

#80

Post by overgard »

alex_suzuki wrote: post #73
overgard wrote: post #14

I think this is a flawed analogy. In the past when we had a new way of doing something that obsoleted the old way, it replaced it because it was an obvious improvement. I mean, stop motion is cool, but obviously there are limitations. The deal GenAI offers is: the result will be mediocre at best, on average it will be slop, but it will do it much faster. Ok, that's a fair value proposition in certain contexts . We've…

My biggest gripe with AI is that I struggle to come up with even one real problem that it has solved in my daily life, and that of my family and friends. Yes it might have made me a bit faster at some things I do for work. But it seems to me that we face so many challenges as a civilization, and AI doesn’t actively help with any of them? Unless you buy into the narrative that it will somehow usher in a golden age of…

> My biggest gripe with AI is that I struggle to come up with even one real problem that it has solved in my daily life, and that of my family and friends.

I wish I could upvote this a thousand times, because this is exactly my experience as well. It's made a few things slightly more convenient, but convenience is not exactly a problem in my life! And yet, it's actively damaging a lot of things I care about in a way that I think is going to be extremely bad for society.

Post reply on HN