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

What we lost the last time code got cheap

poppastring.com

Post reply on HN
Print view View original

111–120 of 126 posts

Re: What we lost the last time code got cheap

#111

Post by larsfaye »

jbvlkt wrote: post #74

I do not understand why this is so unpopular today? I feel like everyone now thinks that basically all of SW engineering is outdated. We are supposed to forget all lessons learned and let agents to go through this? My opinion is to not care who did the job. But we should apply the same standard to human and AI output. I do not buy "we should not look at code". If we should not look at it what we should check instead…

The "don't look at the code" movement is a fad that we simply have to go through to prove that the real problems were never obvious, but lie in the subtle nuances and interplay between all the moving parts of what makes software function in the first place. We have to abuse the tool before we learn to properly use the tool.

Re: What we lost the last time code got cheap

#112

Post by larsfaye »

NuclearPM wrote: post #67
superfrank wrote: post #43

Earlier quoted context omitted.

Maybe it's just because I grew up spending way too much time on the internet, but I write like that and have since well before LLMs. As much as people like to attribute that style to AI, I don't think it's the dead giveaway that people act like it is.

You’re absolutely right. And honestly, you’re really on to something.

Yes—this is the part that nobody is telling you. That's the real shift that is happening.

Re: What we lost the last time code got cheap

#113

Post by larsfaye »

jnovek wrote: post #6
nabbed wrote: post #3

I worried this blog post was going to pivot into a marketing pitch for some product, but no, it just describes the issue where the AI tool that generates your code probably won't document its reasons for the choices it makes. That documentation problem exists in the pre-AI era too, except that the reasons might exist in the heads of your co-workers and could possibly be teased out. I know nothing about AI code genera…

The AI can't really describe its reasoning, though. It can only look at its context history and find a justification (which it will then present as reasoning). In my experience asking the model "why did you do that" carries substantial hallucination risk.

Not only can it not describe its reasoning, it can't "remember" if you ask it later; it can only observe what is. Nor can it be consistent; I've had it shift reasoning numerous times as the questioning continues, only to come full circle to its original statement while it apologizes profusely for being misleading.

The model will always be completing the story you start with it. There's no opinion to uncover because there's no experience that occurred. It's impossible to know where your influence ends and the model's factual basis begins.

Re: What we lost the last time code got cheap

#114

Post by csallen »

Terr_ wrote: post #110
csallen wrote: post #97

Earlier quoted context omitted.

> When code production gets cheap, the cost doesn't disappear. It migrates. I'm surprised people aren't taking the time to edit this very specific kind of phrasing out of their writing. It's such a common AI tell now that, even when writing by hand, I'd just avoid it entirely. Then again, I hated that LLMs co-opted the em-dash, and I refuse to stop using it, so I suppose I get it.

> to edit this very specific kind of phrasing out of their writing Even without touching moral/ethical/normative reasons, it's impractical . LLMs will continue to incorporate the most popular phrasings or grammars, and touchy readers will simply pivot to a new "telltale" du-jour . Eventually any personal or organic writing will be gone, as one twists themselves into an artificial form of "the inverse of the LLM." > M…

> Even without touching moral/ethical/normative reasons, it's impractical.

It's impractical to edit your AI-generated writing to put it in your own voice? People have been writing unique stuff for millennia.

Re: What we lost the last time code got cheap

#115

Post by bluefirebrand »

wiremine wrote: post #79
bluefirebrand wrote: post #71

Earlier quoted context omitted.

> a lot of _human_ written code was/is less-than-fine. And a lot of human devs didn't understand the context when they wrote it. I don't think anyone truly disputes this, but I don't think it's a good argument. If we already had a sort of poor quality output when humans were at the helm, then what can we expect from AI steered by the sort of humans that produced poor quality code? My guess would be even more poor qua…

> then what can we expect from AI steered by the sort of humans that produced poor quality code. Great point, and I think that's my argument: above-average engineers can now produce more above average code. We don't need as many (any?) below-average developers moving forward.

It's possible, but I think unlikely. For one thing, most managers can't really tell who is above or below average. We still in 2026 have "lines of code" as a usual metric for judging the quality of a dev.

So how do you think that will play out in reality?

Re: What we lost the last time code got cheap

#116

Post by YongHaoHu »

wiremine wrote: post #53

> The code they [LLMs] produce is often fine. It works. It passes tests. It might ship as-is. I don't disagree, but I've been thinking about this a bit: a lot of _human_ written code was/is less-than-fine. And a lot of human devs didn't understand the context when they wrote it. I'm not advocating that we fire devs, or evangelizing that LLms are awesome. But I do wish there was a slightly more honest take on the pre-…

[dead]

Re: What we lost the last time code got cheap

#117

Post by jochem9 »

soperj wrote: post #108
wiremine wrote: post #53

> The code they [LLMs] produce is often fine. It works. It passes tests. It might ship as-is. I don't disagree, but I've been thinking about this a bit: a lot of _human_ written code was/is less-than-fine. And a lot of human devs didn't understand the context when they wrote it. I'm not advocating that we fire devs, or evangelizing that LLms are awesome. But I do wish there was a slightly more honest take on the pre-…

> a lot of _human_ written code was/is less-than-fine. At least at my work place this is often the case whenever we bring in contractors who will never be tasked with maintaining their code. Middle management rarely ever gives us the time to fix this broken mess, and when they do, it's actually in a neat maintainable state. We recently took 700mb of compiled code and reduced it to under 40mb just by getting rid of us…

If you're at a stage where code doesn't compile and doesn't do what you want, then that's really easy to improve.

- let the llm (agent) compile the code and iterate until it does.

- state your intent more clearly.

Re: What we lost the last time code got cheap

#118

Post by teiferer »

csallen wrote: post #107
teiferer wrote: post #100

Earlier quoted context omitted.

Why would they have to? Just to avoid being accused of using a slop machine? If that is the only criticism you have against LLM produced text, then there is no problem. And I'm saying this as somebody who is strongly against LLM-generated content of this form.

I have no problem with AI-generated text. But I do have somewhat of a problem with unedited text. Personally, I even take the time to edit my HN comments. And, for the same reason I'd have a problem watching the same episode of the same show every day, I have a problem with reading text that feels like a super derivative clone of tons of other writing. Which is usually what you get when you don't edit your AI-generat…

All good, and I agree.

But the question was about somebody who does write the text themselves, who edits it themselves, no AI has ever touched it, but the result still has elements of what AI text typically has. Because it's their style. Why should such people have to adapt? Just so they don't end up in a witch hunt? How about texts older then 2, 5, 10 years? Should they be changed too? And how about if "LLM style" changes over time?

Re: What we lost the last time code got cheap

#119

Post by Terr_ »

csallen wrote: post #114
Terr_ wrote: post #110

Earlier quoted context omitted.

> to edit this very specific kind of phrasing out of their writing Even without touching moral/ethical/normative reasons, it's impractical . LLMs will continue to incorporate the most popular phrasings or grammars, and touchy readers will simply pivot to a new "telltale" du-jour . Eventually any personal or organic writing will be gone, as one twists themselves into an artificial form of "the inverse of the LLM." > M…

> Even without touching moral/ethical/normative reasons, it's impractical. It's impractical to edit your AI-generated writing to put it in your own voice? People have been writing unique stuff for millennia.

> your AI-generated writing

Hold up, the subject was writing which is not "AI generated", and the edits authors might make out of fear of being falsely accused.

If that's not what you intended, then I think your earlier comment is in error, since I'm not the only one who read it that way.

Post reply on HN