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

A coder considers the waning days of the craft

newyorker.com

Post reply on HN
Print view View original

931–940 of 1001 posts

Re: A coder considers the waning days of the craft

#931

Post by crabmusket »

4death4 wrote: post #269
crabmusket wrote: post #264

Earlier quoted context omitted.

> As a thought experiment for the reader: consider a complex system you've worked on. And now try to imagine writing down a specification for the system in natural language that an LLM could use to generate the code that powers the system. But you didn't write it down, so how did the system get made? The answer is that the program exists in your head as much as it exists in bytes in your source files. There might be…

> But you didn't write it down, so how did the system get made? We didn't write it down, but we did use natural language to specify it, albeit somewhat indirectly. Some of the specification came from meetings with leadership, PMs, other people in the org, customers, etc. Some of it came from getting drinks with the team and talking about what we wanted to build. Some of it came from conversations with ex-colleagues.…

Exactly my point! What you were doing was theory-building, creating a mostly-shared mental understanding of the program.

Re: A coder considers the waning days of the craft

#932

Post by nylonstrung »

clnq wrote: post #482
danenania wrote: post #197

Earlier quoted context omitted.

What’s your niche? I think much of using it well is understanding what it can and can’t do (though of course this is a moving target). It’s great when the limiting factor is knowledge of APIs, best practices, or common algorithms. When the limiting factor is architectural complexity or understanding how many different components of a system fit together, it’s less useful. Still, I find I can often save time on more d…

My niche is in video game programming, and I am very specialized in a specific area. So I might ask things like how would one architect a certain game system with a number of requirements, to meet certain player expectations, and be compatible with a number of things. Unfortunately, it hasn’t been helpful once, and often due to the same reason - when the question gets specific enough, it hallucinates because it doesn…

I think GPT is comparatively poor at game dev due to a relatively small training corpus, with much more code being locked away in binaries (.uproject, etc), and game code rarely being open sourced

Godot might benefit more than other engines, since much of the code is stored as plaintext GDscript and makes it to GitHub more frequently

Re: A coder considers the waning days of the craft

#933

Post by Kailhus »

sensanaty wrote: post #514

Whenever I see people talking about how they use ChatGPT to write entire software suites, I feel like I'm taking crazy pills or something. I can't even get GPT4 to give me decent basic ass Ruby scripts where it opens a file that doesn't have some weird behavioral quirk or footgun, yet people often claim that they're doing insane feats with it all the time. My experience, even if I'm just trying to be lazy and have it…

I’ve had the same experience. Moreover, had to deal with some questionable code from colleagues which looked fine during reviews but as soon as you use it within context the control flow is totally out of whack resulting in by the weirdest debugging sessions. Not cool

Re: A coder considers the waning days of the craft

#934

Post by awinter-py »

simonw wrote: post #196
awinter-py wrote: post #109

this is by james somers! long arc from 'there's a gold rush and I'm the shovel' back in the day

I guess you mean this article from 2013 https://aeon.co/essays/dad-s-company-made-burgers-mine-just-... ?

yes

this really landed for me when it came out

his 'you are reading the wrong dictionary' on his blog is also good

Re: A coder considers the waning days of the craft

#935

Post by hnick »

galaxyLogic wrote: post #275
cglan wrote: post #6

Maybe I’m in the minority. I’m definitely extremely impressed with GPT4, but coding to me was never really the point of software development. While GPT4 is incredible, it fails OFTEN. And it fails in ways that aren’t very clear. And it fails harder when there’s clearly not enough training resources on the subject matter. But even hypothetically if it was 20x better, wouldn’t that be a good thing? There’s so much of t…

To me best part of AI is I can ask it a question and then a follow-up question, about how some code- or API construct works. THEN I can ask it a follow-up question. That was not possible before with Google. I can ask exactly what I want in English, not by entering a search-term. A search-term is not a question, but a COMMAND: "Find me web-pages containing this search-term". By asking exactly the question I'm looking…

This is the main benefit I get from the free ChatGPT. I ask a question more related to syntax e.g. how to make a LINQ statement since I haven't been in C# for a few weeks and I forget. If it gets things a little wrong I can drill down until it works. It's also good for generic stuff done a million times like a basic API call with WebClient or similar.

We tested CoPilot for a bit but for whatever reason, it sometimes produced nice boilerplate but mostly just made one-line suggestions that were slower than just typing if I knew what I was doing. It was also strangely opinionated about what comments should say. In the end it felt like it added to my mental load by parsing and deciding to take or ignore suggestions so I turned it off. Typing is (and has been for a while) not the hard part of my job anyway.

Re: A coder considers the waning days of the craft

#936

Post by gymbeaux »

gavmor wrote: post #152
gymbeaux wrote: post #134

Earlier quoted context omitted.

Yeah it’s not a challenging problem, but the specific code example isn’t the point. Replace his example with “at one point, we wanted a command that would convert a PNG to a JPG….” most of us couldn’t do that without Google.

$ cat /usr/share/dict/words | shuf | head -n 10 $ convert foo.png foo.jpg Took me almost literally two seconds to come up with that, unless your point is that at one point I had to learn it which, yeah, sure. What am I missing?

Well, convert does the conversion for you… it’s kind of challenging to come up with an example where there isn’t already a tool/package/library for X. But like pretend there wasn’t one for converting images… you can’t just off-the-cuff that.

Re: A coder considers the waning days of the craft

#937

Post by disqard »

aerhardt wrote: post #560
ken47 wrote: post #371

It feels like this article was not written by a programmer, and it feels like a number of the commenters are not professional engineers. What part of a programmer jobs can AI realistically replace in the near term? For the sake of argument, let’s say it could replace the coding part cost effectively . Can it still do all the other parts? Take ambiguous requirements and seek clarity from design, product, etc. (instruc…

The article was totally written by a programmer though, what would make you say that?

Like many other communities, programming has historically had its share of gatekeeping, and it's often easy to forget that "programming" spans a wide range of abilities and skill levels.

So, while GP might be technically correct in some narrow sense, I would be less quick to judge the OP article author. Some years hence, anyone who is not actively building (as opposed to using) one of these LLMs might be dismissed as "not a real programmer" (because by then, that will be the only form of programming in existence).

Re: A coder considers the waning days of the craft

#938

Post by clnq »

somestag wrote: post #904
clnq wrote: post #482

Earlier quoted context omitted.

My niche is in video game programming, and I am very specialized in a specific area. So I might ask things like how would one architect a certain game system with a number of requirements, to meet certain player expectations, and be compatible with a number of things. Unfortunately, it hasn’t been helpful once, and often due to the same reason - when the question gets specific enough, it hallucinates because it doesn…

Interesting. I also work in game development, and I tend to work on project-specific optimization problems, and I've had the opposite experience. If I have to solve a hairy problem specific to our game's architecture, obviously I'm not going to ask ChatGPT to solve that for me. It's everything else that it works so well for. The stuff that I could do, but it's not really worth my time to actually do it when I can be…

Well, I think most software engineers in games don’t work all that much with scripts or database queries, nor write that many tests for systems of scale that GPT could produce. You might be in devops, tools, or similar if you deal with a lot of that in game dev.

GPT code in a lot of critical path systems wouldn’t pass code review, not probably integrate well enough into any bespoke realtime system. It seems to be more useful in providing second opinions on high level decisions to me, but still not useful enough to use.

Maybe it could help with some light Lua or C# gameplay scripting, although I think co-pilot works much better. But all that doesn’t matter as due to licensing, the AAA industry still generally can’t use any of these generative AIs for code. Owning and being able to copyright all code and assets in a game is normally a requirement set by large publishers.

To conclude, my experience is indeed very different from yours.

Re: A coder considers the waning days of the craft

#939

Post by 4death4 »

crabmusket wrote: post #931
4death4 wrote: post #269

Earlier quoted context omitted.

> But you didn't write it down, so how did the system get made? We didn't write it down, but we did use natural language to specify it, albeit somewhat indirectly. Some of the specification came from meetings with leadership, PMs, other people in the org, customers, etc. Some of it came from getting drinks with the team and talking about what we wanted to build. Some of it came from conversations with ex-colleagues.…

Exactly my point! What you were doing was theory-building, creating a mostly-shared mental understanding of the program.

Ah, ok. I see. I originally interpreted your comment as “there was some natural language spec, therefore you could feed it into an LLM” but I see I was mistaken.

Re: A coder considers the waning days of the craft

#940

Post by clnq »

throwaway4aday wrote: post #885
clnq wrote: post #482

Earlier quoted context omitted.

My niche is in video game programming, and I am very specialized in a specific area. So I might ask things like how would one architect a certain game system with a number of requirements, to meet certain player expectations, and be compatible with a number of things. Unfortunately, it hasn’t been helpful once, and often due to the same reason - when the question gets specific enough, it hallucinates because it doesn…

I'm interested to know if you've tried creating a custom GPT with their builder or the API. If you have enough old example code, notes, or those rare textbooks you mention you could add those as files and see if the built in RAG improves the answers it gives.

I tried building a custom GPT but the training data it has is not sufficient, no matter how well it’s steered.

Documents and code are confidential in the AAA games industry as they are the money makers. Developers are not free to hand them over to third parties, that would be known as a leak. With textbooks, that would be a pretty grey area use case. So I’ve not experimented with that.

I think it could help, but because it’s so infeasible practically, there’s no incentive to try this with synthetic data, too.

Post reply on HN