TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

If AI is helping people code better, why aren't products getting better?

120 pointsby thisismytest8 months ago
If AI is helping people code a lot faster and better, why aren’t the products I regularly use getting way better?<p>Source: <a href="https:&#x2F;&#x2F;x.com&#x2F;staysaasy&#x2F;status&#x2F;1837812645946126560" rel="nofollow">https:&#x2F;&#x2F;x.com&#x2F;staysaasy&#x2F;status&#x2F;1837812645946126560</a>

90 comments

shepherdjerred8 months ago
Why would there be a correlation between how fast something is developed and its quality?<p>Assuming that AI is helping developers to write more code, it could mean:<p>* there are fewer developers<p>* developers are working less<p>* the efficiency gains are resulting in more products being created rather than existing products being improved<p>* AI isn&#x27;t widely enough adopted or used to make enough of a difference<p>* the benefits are too recent to be measured
评论 #41626036 未加载
评论 #41621534 未加载
评论 #41621356 未加载
评论 #41622928 未加载
评论 #41621363 未加载
评论 #41625346 未加载
PaulHoule8 months ago
There&#x27;s a time delay between when an innovation is first adopted and when it has a real impact. You might spend anywhere from 2 months to 8 years [1] developing an application. I&#x27;ve seen numerous VC or bootstrapped companies that took 1.5 years to 2 years to launch, so I wouldn&#x27;t expect AI to have had much an effect yet.<p>I&#x27;m also not sure about &quot;better&quot;; I find Copilot is a good wingman for writing things like shell scripts, CMD.EXE scripts, powershell scripts and python scripts that do simple things. Even there I find it confuses forward slashes and backslashes sometimes so I often have to do a little debugging. Copilot can help me figure out how to use obscure (to me) features of PostgreSQL in JooQ. It will also argue with me and take factually wrong positions such as telling me that there is no zero-argument version of Optional.orElseThrows() which there is.<p>[1] <a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Concord_(video_game)" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Concord_(video_game)</a>
评论 #41626652 未加载
评论 #41629778 未加载
评论 #41627064 未加载
cdf8 months ago
AI code assistants are amazing when you start from zero and just need a 80% working prototype. But once you start trying to refine the product from there, that&#x27;s where the automation gets counterproductive. If you can exactly specify the problem, eg &quot;Password input crashes when the password has an apostrophe&quot;, AI can probably fix it. But if the bug report comes in as &quot;Password input randomly crashes&quot;, I will be very surprised if AI can figure out why and fix it. Where a human wrote the code, he or she may figure out why fairly quickly. Now, if you want a human who didnt write the code to understand the AI generated code, it may take a lot longer. In fact, in all likelihood, the AI assisted products are likely to be buggier and stay so longer, esp if companies start to think they can fire the senior devs and hire less skilled devs and fill the gap with AI. At some point, the pendulum will swing back, and companies will be chasing devs again.
评论 #41622497 未加载
DanHulton8 months ago
Simple, really. It&#x27;s not actually helping people to code better:<p><a href="https:&#x2F;&#x2F;greaterdanorequalto.com&#x2F;ai-code-generation-as-an-agent-of-tech-debt-creation&#x2F;" rel="nofollow">https:&#x2F;&#x2F;greaterdanorequalto.com&#x2F;ai-code-generation-as-an-age...</a>
评论 #41626354 未加载
评论 #41626495 未加载
turnsout8 months ago
The simple answer is that product managers are not asking for quality. They&#x27;re asking for cards&#x2F;stories to be completed. &quot;Quality&quot; has been redefined as &quot;meets requirements&quot; or &quot;passes UAT.&quot; Actual quality is just not in anyone&#x27;s KPIs or OKRs.<p>That&#x27;s why it&#x27;s way easier for indie developers to deliver high-quality software—their incentives are directly aligned with the user.
评论 #41627089 未加载
JeffeFawkes8 months ago
My theory... Being able to code well or fast doesn&#x27;t one to one translate to a good end user experience. The strength of your org&#x27;s ability to determine good features and iterate on them from a product perspective is what matters, and that &#x2F;can&#x2F; potentially happen faster if AI is enabling faster development, but it&#x27;s not guaranteed.<p>Even if we had a magic box that results in perfect code coming out every time for a given feature description, that doesn&#x27;t mean the feature itself is good or well thought out.
评论 #41626746 未加载
ado__dev8 months ago
We&#x27;re still very much in the early days.<p>Code AI tools today absolutely crush at creating proof of concept apps. You can test your idea and get market validation in days vs months.<p>They are getting better at medium&#x2F;large codebases, but still have a ways to go before being super useful and it translating to a huge increase in productivity. Currently it&#x27;s really good for helping with the menial tasks (creating docs, unit tests, understanding and onboarding) but not quite there yet when it comes to integrating gen ai code in large codebases, but it&#x27;s only a matter of time.
评论 #41622283 未加载
评论 #41621344 未加载
评论 #41621352 未加载
poniko8 months ago
My experience with AI as a coding parter is yes, great at just doing boring things like take this list and give me an enum or add a form for this class etc .. but when I do anything remotly advanced it breaks apart, especially bad at dotnet where there are 25 years worth of history it source code from .. often it creates somthing that is long out of date, and jesus it tried to rewrite the same code ten times to solve a problem that was not supported by framework and could not be solved. So yea .. give it some years I guess. Still use it daily and I still need to fix Ai generated bugs ..
animal_spirits8 months ago
All of the products you are using today were likely created before ChatGPT was released. For those products, you are not going to see any visible improvements because many of them will suffer from poor implementation due to lack of adequate knowledge of code&#x2F;frameworks. Most software best practices are learned after the software is created and release. The code is probably very spaghetti and hard to maintain. Refactoring is still hard for AI, but writing from scratch is much easier with AI. For the software that is currently out, bugs will be fixed faster, and features might be added sooner.<p>The real explosion of great software will happen in 3-5 years. AI is huge for the beginning of projects. You know _what_ you want the app to do but you don&#x27;t know _how_. That&#x27;s where AI adds huge value. People are now starting new projects with AI help, and they are building foundations of codebases that will be much more maintainable and sustainable as development continues compared to the current suite of software products we interact with today.
评论 #41621345 未加载
评论 #41621361 未加载
giantg28 months ago
&quot;If AI is helping people code better, why aren&#x27;t products getting better?&quot;<p>Because it&#x27;s not helping them code better. It might be faster, but the quality in my experience is worse. Then the user is trying to verify or troubleshoot code they didn&#x27;t write.<p>The bigger issue is garbage in, garbage out at the requirements level. The business hardly ever documents their business system before turning it into a technical system. How can we create a system to meet requirements that nobody knows and didn&#x27;t have a chance to really think about while writing the code?
alentred8 months ago
Because Code ≠ Product. Code ∈ Product, among many other things.<p>I would go even further and say that that relationship between the two is weak, but also very peculiar: bad code <i>can</i> ruin a good product; but good code alone says very little, if anything at all, about the quality of a product.
评论 #41626640 未加载
评论 #41626507 未加载
评论 #41627106 未加载
userbinator8 months ago
AI only helps those who are below-average to become (barely) average --- and that average is dropping. Also, quantity is not quality.
评论 #41626165 未加载
furyofantares8 months ago
1. They probably are. I&#x27;m sure I would notice a 500% increase in the rate that products get better, but I&#x27;m also sure I wouldn&#x27;t notice 10%, which is much more realistic (but imo it&#x27;s probably still less.)<p>2. Productivity gains don&#x27;t go directly to products getting better. Individual developers may choose to realize some gains by spending more time with their family. Of course the company will claw that back but it takes time. And when they do, some of the gains may instead be realized by higher profit margins rather than better products and it will take time for consumers try to claw that back using their market choices.<p>3. Companies have lots of moving parts and a speed they&#x27;re used to going; it will take time to adjust if one part goes a little faster.<p>4. LLM-assistants help a lot with getting up to speed in a new field or making stuff from scratch, and a lot less for a skilled team who already knows all the product code and surrounding tools. So &quot;products you use regularly&quot; benefit the least.
blibble8 months ago
bad developers emitting more code has never led to anything good<p>unless you&#x27;re being paid to clean up the mess<p>it&#x27;s like outsourcing on steroids
spit2wind8 months ago
Programming with AI, so far, tries to specify something precise, algorithms, in a less precise language than what we have.<p>It&#x27;s the difference between Euclid and modern notation, with AI programming being like Euclidean notation and current programming languages being the modern notation:<p>&quot;if a first magnitude and a third are equal multiples of a second and a fourth, and a fifth and a sixth are equal multiples of the second and fourth, then the first magnitude and fifth, being added together, and the third and sixth, being added together, will also be equal multiples of the second and the fourth, respectively.&quot;<p>versus<p>a(x + y) = ax + by<p>If AI programming can find a better way to express the problems we&#x27;re trying to solve, then yes, it could work. It would become a matter of &quot;how well the compiler works&quot;. The current proposals which use natural language as the notation is not better than what we have.
评论 #41626588 未加载
Jtsummers8 months ago
Some possibilities:<p>1. The products you use are not developed by people using LLMs.<p>2. The products you use may be using LLMs in development, but only recently so you&#x27;ll see a delay before any improvement.<p>3. The products you use are using it, and maybe it&#x27;s helping with quality, but not anywhere that users care about or notice.<p>4. The products you use are using it, and it&#x27;s not helping with quality, just churning out more code.
DonsDiscountGas8 months ago
Writing the same code 10% faster isn&#x27;t necessarily going to make it better. Also the biggest improvements have been among novices, and the products you regularly use were predominantly written (or at least reviewed) by more experienced people.
SkyBelow8 months ago
Better programming, task to task, does not result in better applications.<p>For a simple example, consider a would be program that takes 100 tasks of 16 hours each to build a program with a quality of 75%. With AI, those tasks can take an average of 12 hours each, meaning the software can be delivered faster. Unless someone purposefully invests the saved time into improving the program, you&#x27;ll end up with the same 75% quality program faster.<p>Now what if AI makes the code slightly worse, leading the quality to drop to 70%, but some of the savings are used to improve quality, bringing it back up to 75%? Same outcome of the product not being any better to the end user.<p>Even if the code is higher quality, how much of that 25% of missing quality is the result of bad code verses bad designs or a mismatch between what customer wants and what those designing the project think the customer wants? Even a perfect AI that solves all bugs won&#x27;t improve that.<p>In short, programming better can mean many different things, some of which might translate to a better or worse product, but with no consistency.
CM308 months ago
Because the quality of the code is at best very, very loosely related to the quality of the end product. I mean, what are many of the issues you see in poorly designed sites, apps, programs, etc?<p>Usually a mix of poor design choices and hostile design.<p>Neither of these directly correlate to the quality of the code, how quickly it was created, how many bugs it has, etc.<p>If everyone working in tech (or any sort of programming related project in general) was an expert level programmer with decades of experience, neither of these things would be noticeably better. They&#x27;d still create software that&#x27;s miserable to use because of bad design, and we&#x27;d still have companies trying to scam the users by making basic functionality hard to use (see cookie notices, unsubscribe processes, etc).
csallen8 months ago
I signed into Zapier yesterday for the first time in a while. You can seemingly run their entire UI right now via AI. I typed a simple idea into their AI box, and it created a multi-step &quot;zap&quot; for me that was more-or-less what I wanted.<p>So at least some software is getting better.
评论 #41621335 未加载
benreesman8 months ago
Because like any tool, it can be used thoughtfully and it can be used carelessly.<p>There are use cases where LLMs help with coding (and they are growing as the things get better), but even if they could do as well as an experienced engineer at doing a first draft (which, debatable in any setting and falls off sharply once it&#x27;s not a highly mainstream setting), a first draft is almost never a high-quality artifact.<p>They can also be used to get a sort of minimum viable diff that represents a liability to the codebase and those who maintain and depend on it, to do this with very little effort and therefore impose the negative externalities on someone else. Anecdotally this seems to be a distressingly common use case. I&#x27;m more than a little concerned that software quality is about to take an abrupt turn for the worse in aggregate.<p>More broadly, if you&#x27;re anything like most people I know, the products you&#x27;re using are getting better all the time... at making money for the companies that build them. Consumer Internet profits and&#x2F;or valuations are at something like an all time high. All that lag and jank and spam and shit? That&#x27;s not easy code to write or simple infrastructure to operate. That&#x27;s full-metal-jacket monetization at great effort and expense.
Chris_Newton8 months ago
I think of the current generation of AI coding tools as being like a developer with a little bit of experience in almost any tech stack and field of application.<p>If I’m investigating a new field or trying out a new language or library, relative to my own experience, then it’s quite common for an AI code generator to use idioms or libraries I hadn’t yet come across. That alone sometimes saves me a useful amount of time doing research.<p>However, it’s almost all breadth and very little depth. The quality of the generated code is rarely better than something a junior-to-mid-level developer might have written. It needs to be reviewed and corrected with similar diligence.<p>Similarly, the quality of a generated review of existing code or of generated supporting assets like test cases or documentation is often superficial and error-prone. I rarely find it an overall win to use current AI-based tools for these things instead of existing tools that can’t do as much but are consistent and reliable at what they do do.<p>So I wouldn’t necessarily expect current AI tools to help me code <i>better</i>, only sometimes a bit <i>faster</i>, and that mostly in new areas I’m exploring rather than areas where I’m doing professional work that is going to get shipped in the near future.
obirunda8 months ago
I think the primary reason is that datasets contain a lot more average&#x2F;bad code than exceptional, and to add to that problem judging between those is possibly a subjective issue.<p>Developers using AI will get mostly average solutions faster but exceptional ones will be obviously rare. And, crucially if the idea itself is average or bad there isn&#x27;t much an elegant coding solution will do for the idea.<p>I think this ultimately is the divide between the hype and reality of how AI will impact products. If you just give a product manager the keys to do all the coding as no code &quot;prompt engineer&quot;, more than likely will lead to further enshitification of features in products with unmaintainable code bases. At the current state, understanding algorithms and thinking computationally is a requirement to improve a code base.<p>The hopes of having a &quot;build me a $1 billion app&quot; prompt capability, or &quot;improve my shitty app&quot; are too long horizon and subjective requests to bypass the hardships of product ideation and iteration to have the LLM deliver on the requests. It&#x27;s not magic, it&#x27;s probability. Averages are the end goal here, not excellence.<p>If we arrive at a point where LLMs translate general prompts into idealistic versions that are more like version 100 of the idea while still capturing the user&#x27;s intent, then we will see these improvements. Otherwise it&#x27;s copy pasta on steroids, and done mindlessly, will mostly lead to enshitification rather than improvements.
jccalhoun8 months ago
I have been messing around with a project using python on a raspberry pi. I know a little javascript but I&#x27;m no programmer and didn&#x27;t know any python and hardly anything about linux before this. Chatgpt and Gemini have helped me a lot by writing code that included common libraries that I didn&#x27;t know existed. Then I can modify it and tweak it to suit my needs.
dfxm128 months ago
<i>Crucially</i>, products are more than &quot;code&quot;. They are UX, they are support, they are maintainability, etc.<p>Also, in my experience, AI is helping people who don&#x27;t know how to code to write code they don&#x27;t understand and can&#x27;t support. In my experience, the people who are already making products aren&#x27;t getting much benefits from AI (not yet anyway).
layer88 months ago
AI makes it easier to build a mediocre or just barely working product, hence rather a decline in quality is to be expected.
mindwok8 months ago
An improvement in productivity does not necessarily imply improvements in quality. Where those extra engineering hours get spent is determined by management, and management are optimising for profit, which could mean optimising for quality but more likely means optimising for feature development.
mrtomservo8 months ago
This is a personal anecdote, and just one data point, but still. I work on websites for customers, and frequently I&#x27;ll need to (for example) iterate through some spreadsheet data, or convert a big object of this format to some other format. These are tedious tasks that don&#x27;t take a _huge_ amount of time, but instead of grinding on a particular function for 30 minutes, I have a workable thing I can tweak in five minutes. I&#x27;d say this helps me &quot;code faster and better.&quot;<p>Does it make the end product better? Not really: I would have gotten there with a function written by me or some LLM. But like everything I&#x27;ve been asked to do my professional career, it allows me to do more with less. More dumb functions in less time.
breck8 months ago
You&#x27;re using the wrong products!<p>1. Look for products that don&#x27;t have (c)opyright. Any product still using that or licenses is going to evolve too slow and go extinct.<p>2. Look for products built on revolutionary simpler stacks like PPS.<p>I thought this was going to be an essay and not just a Tweet, so I did record a long winded response, which I think contains a lot of relevant info: <a href="https:&#x2F;&#x2F;news.pub&#x2F;?try=https:&#x2F;&#x2F;www.youtube.com&#x2F;embed&#x2F;KhDvFNefvuU?si=xWWtKewSZe3V1j7i" rel="nofollow">https:&#x2F;&#x2F;news.pub&#x2F;?try=https:&#x2F;&#x2F;www.youtube.com&#x2F;embed&#x2F;KhDvFNef...</a>
Pinkthinker8 months ago
I’m old enough to remember databases like IDMS before SQL came along. SQL simplifies database access in a similar way to how AI and low-code tools simplify application that have minimal logic - things like web pages, dashboards and the like. But the moment you need to do something at the other end of the spectrum - like a complex financial model - they fall down completely. That’s because you need someone to program the logic. Right now, only a programmer can do that. New tools are on the way, but they don’t use LLMs
j458 months ago
Maybe things that weren&#x27;t being built (available capacity to develop) is increasing, thereby lifting up the floor of things that never get built.<p>Further, non-coders being able to become equivalent to a junior developer is a huge leap.<p>What active developers do with AI remains to be seen. It really could 20x the average developer, but it doesn&#x27;t seem like a huge chunk of developers are really using AI in a way that it&#x27;s the rage on the developer level broadly.<p>Maybe that&#x27;s why Cursor going &quot;viral&quot; on youtube seems different when it was known to some, and not others.
Fifolu8 months ago
Having used a lot of these AI tools and products over the last two years, my experience is, while these tools are useful for creating MVPs with better UIs than before, a lot of work still needs to be done to scale the applications and systems you are building. Therefore, there is still probably as many developers or more working within organisations and not much have changed in terms of the quality of work being produced.
stephenr8 months ago
&gt; If AI is helping people code a lot faster and better<p>You may as well ask why the advent of StackOverflow didn&#x27;t massively increase app quality, it&#x27;s the same target audience.
HumblyTossed8 months ago
I don&#x27;t think things are going to get &quot;better&quot;. I think you&#x27;ll see some homogeneity, where a lot of code will just converge at &quot;average&quot;.
at_a_remove8 months ago
I believe it increases the speed of the <i>coding</i>, but not the quality. It doesn&#x27;t do your QA for you. It doesn&#x27;t do your UX for you. And if you&#x27;re a code monkey assigned to implement a feature you know will drag the product down, well, you&#x27;ll get that out the door faster. AI won&#x27;t force the marketing people to make good decisions, or create sane deadlines, and so on.
SkyPuncher8 months ago
Product development decisions are essentially completely independent of software development decisions. Product development is challenging in it&#x27;s highly contextual, highly political, and essentially unique to every product.<p>It doesn&#x27;t how effective software development is if you&#x27;re not doing anything to improve the discovery and planning process.
nrjames8 months ago
I don&#x27;t find them useful for coding much, but I do find them useful for searching through documentation and making suggestions. With Cursor, you can have it reference the docs for the library&#x2F;framework you are using and then ask it questions about the docs. While this does not always work well, it can save a lot of time.
yatz8 months ago
In my experience, AI is helping people code faster, not precisely better! It does not take long before we find the limitations of AI code-gen running you in circles.<p>As far as I know, most of us do research with AI to get ideas and find pros and cons but we are still the ones mostly driving the logic with AI filling in the function level blocks.
j7ake8 months ago
They don’t code better but they code faster.<p>I imagine for first pass prototypes, AI will greatly accelerate the process. But getting to the fine details and getting things done well will still take same amount of time.<p>AI-guided coding will help code up “good enough” implementations, which is great for research and testing ideas but not for production.
gadders8 months ago
I think it is helping them generate the same code faster, rather than generate code with different functionality.
johnea8 months ago
How many times are these naive questions going to resurface?<p>Of course this all depends on what you mean by &quot;better&quot;, or for whom the product is better.<p>AI, like every technical advance in history, will be deemed &quot;better&quot; if fewer people make more money from it.<p>This has nothing to do with you, mister insignificant user...
amadeuspagel8 months ago
At this point, I&#x27;d expect to see more new products, especially more web apps. Are there? Would be interesting to look at &#x2F;show with that in mind. I know I&#x27;m creating things I couldn&#x27;t without AI. I expect more people who aren&#x27;t web devs to make web apps.
sitkack8 months ago
W&#x2F;o a different incentive structure, nothing will get better from what it is now. And if there is a way to produce something cheaper and a functionally equivalent lower quality, that is what will happen.<p>For most part, it will be same quality or lower at a cheaper cost delivered faster.
TechRemarker8 months ago
AI is helping more people code problems they might not be able to on their own or help people do it more quickly for a particular issue but don’t think that in general is making people better coders just like Google auto correct isn’t making people better spellers.
jaredwiener8 months ago
My guess would be that the hurdle in creating better products isn&#x27;t in code completion.<p>User research, UX improvements, feature ideation and creation, etc, are all the same as they have always been. Getting the code out faster doesn&#x27;t help if its in service of a bad feature.
Cthulhu_8 months ago
Because the quality &#x2F; goodness of a product has little to do with the underlying code. Second, is it actually helping people code better? That&#x27;s a claim that needs some paperwork to back it up, and first off all with a definition of &quot;good&quot;.
adamnemecek8 months ago
It has been around for what, a year?
评论 #41621282 未加载
erichmond8 months ago
What is the correlation between &quot;writing code&quot; and product management getting better?
zabil8 months ago
Because coding assistants depend on the baselined code they are trained on for their suggestions?<p>I don&#x27;t believe they offer creative solutions, just a faster way to refer. So it&#x27;s still the responsibility of developers bring their creativity to the process.
deafpolygon8 months ago
People are still learning how to utilize AI in its current form. It will take time for people to integrate this style of tech into their workflows, as well as time for new applications to be developed and released.
tonyoconnell8 months ago
My products are so much better because of AI. I can now build things I didn&#x27;t even dream of building before. I am amazed that so many humans find it really hard to accept this new reality - computers can write better code than we do.
评论 #41623508 未加载
jedimastert8 months ago
Does anyone know if Github has any sort of public telemetry data (of if anyone from GH is around here somewhere)? There was a ChatGPT outage about a month ago and I&#x27;m DEEPLY curious if there was an overall drop in commit volume.
评论 #41622746 未加载
protocolture8 months ago
Dunno, what products do you regularly use?<p>I know my hobby stuff is getting better. I generally dont make front ends for my projects, but genai has helped me build widgets for other front ends, and css&#x2F;js frontends for a lot of my nonsense.
rsynnott8 months ago
If pigs can fly, then why aren&#x27;t there more bacon-scented aviation accidents caused by them getting sucked into jet engines?<p>Like, there&#x27;s little reason to think that LLMs are helping people code better.
ridicter8 months ago
I&#x27;m a designer=engineer, and I feel like AI has given me super powers. Design has always been easy for me--it was just the incredible grind of coding that made creating my own thing difficult.
leshokunin8 months ago
The way the question is framed invites a justification: &quot;why it could be improving while not improving&quot;.<p>I&#x27;m sure there are hypotheses. But it&#x27;s also likely that things are simply not improving.
analog318 months ago
One could look back at history and ask how long it took for better coding tools to result in better software. This could go all the way back to programming languages, IDEs, frameworks, etc.
readyplayernull8 months ago
Better products require better features and better quality. Features are defined by managers, quality is controlled by testing. These haven&#x27;t benefited from AI as much as coding did.
tensility8 months ago
It&#x27;s partially a product of Amdahl&#x27;s Law. Coding and related textual activities are only a fraction of the work required for product design, implementation, and maintenance.
jasfi8 months ago
The AI coding tools I see today help to make coders somewhat more efficient. That isn&#x27;t something that&#x27;s very visible in the software landscape as a whole.
medion8 months ago
Because technology generally makes things faster, not better.
t0bia_s8 months ago
There are two categories of technology. Those which get job done faster and those which get job done easier. Most of nowadays technology belongs to first category.
thefz8 months ago
Because AI is trained on public available code with no indication of its quality, so it&#x27;s churning out the already low quality code it finds online.
lmm8 months ago
Because code quality probably wasn&#x27;t the bottleneck on product quality, and even if it was then some analogue of Amdahl&#x27;s law applies.
AlexCoventry8 months ago
I don&#x27;t think AI code helpers really understand how to make code which is readable and maintainable, at this stage.
lvl1558 months ago
Because it won’t help subpar coders and “100x” types have moved into AI. Meaning, they’re the ones building the tools.
vouaobrasil8 months ago
Duh. Products are not about making life better. They are about stimulating basal instincts for information and novelty. If a company can do that with a horrible user experience, they will. Although I personally have never used substances or drugs, I think it must be similar to drug addiction. Provide just enough of new technology as fast as possible to keep the users high and addicted.
评论 #41626415 未加载
trumbitta28 months ago
AI is helping people code a lot faster. For &quot;better&quot;, you still have to put the work in.
apwell238 months ago
followup question: Why is AI productivity gains showing up in quarterly reports.
stevage8 months ago
Where did that premise come from?<p>Copilot mostly helps people code faster, or with less knowledge required. I&#x27;d expect output quality to go down, not up.<p>And it&#x27;s like anything in capitalism. Companies could choose higher quality, but instead they do whatever gives the highest profit. which is usually adequate quality at low cost.
wheatgreaser8 months ago
for me, AI just speeds up the easy part of the programming. i still have to deal with the hard parts that deal with edge cases and incomprehensible bugs
ddgflorida8 months ago
Too early and code quality isn&#x27;t as good as you think.
aristofun8 months ago
Because ai has not been trained on quality codebases :)
cnotv8 months ago
Because the problem is not in the code itself? :D
gloyoyo8 months ago
Was just thinking this same thing this morning.
feverzsj8 months ago
A toy can only make you happy ... for a while.
ayushl8 months ago
Because they&#x27;re getting fired
purple-leafy8 months ago
<i>faster and </i>worse quality
rbnphlp8 months ago
Quantity vs Quality really .
outlore8 months ago
High quality products result from the accumulation of fixes and polish. They also add new desirable features in response to user feedback.<p>Whether AI is used to write code is irrelevant to a product getting “better”. AI copilots can be used to bootstrap early stage concepts which might be unpolished, or can be used to add polish by writing bug fixes.<p>I neither subscribe to the mania around AI, nor do I think it will enshittify products. I believe it is just another tool that we can use.
deterministic8 months ago
&gt; If AI is helping people code better<p>I don&#x27;t think it is?<p>30+ years of experience here and I haven&#x27;t seen any AI coding examples that makes me want to use AI for coding.<p>It might happen one day but so far nope.
rmellow8 months ago
Digital distribution and cloud apps lowered the cost to correct mistakes and therefore lowered the barrier to release.<p>No longer are developers bound by physical media, or have to force clients to troubleshoot, manually download updates on their website and install them.<p>... and as others said, LLMs impact is greater on junior developers, and at that, more on speed than quality. For experienced developers, the impact is greater on speed.<p>I have no data, only sense to make.
Yawrehto8 months ago
The key is that <i>if</i>. What if it isn&#x27;t, yet? What if right now the AI is in a phase where it&#x27;s still learning and doesn&#x27;t produce good stuff yet?<p>Besides, products have been getting worse for a while. Enshittification is a potent force, and even if AI was axiomatically helping people code faster and better, enshittification might still lead them to add in annoyances, privacy risks, et cetera.
whoomp123428 months ago
ahhh the classic &quot;I confused speed with quality&quot; argument
fennecbutt8 months ago
Because profits.
TechSquidTV8 months ago
Are they not?
stego-tech8 months ago
It&#x27;s complex - an essay in and of itself if we&#x27;re to respond properly, but I&#x27;ll try to keep things brief here.<p>First, let&#x27;s address the tooling side. While the current crop of &quot;code completion tools&quot; built out of or around LLMs are quite capable in their own right, they&#x27;re not exactly &quot;free thinkers&quot; like we can be. Rather, their output is limited by a combination of training data, the model itself, and - increasingly - the user&#x27;s ability to put their ideas into a prompt that can generate the desired output consistently. So there&#x27;s already a huge hurdle just on the tooling side to overcome before we can begin &quot;improving&quot;, one tied just as much to the capabilities of the product as the capabilities of the end user. I would argue that this is the most immediate hurdle to cross if we want to see meaningful improvements to code as a whole.<p>In addition to that immediate hurdle, there&#x27;s three more issues on the tooling front:<p>* The existing training data is largely bad, bloated, or insecure code samples (generally from publicly-available social media and repositories), because code security and efficiency are only relatively recent prerogatives of large development companies or outfits as they seek to dodge lawsuits (security) and increase margins (efficiency)<p>* LLMs aren&#x27;t very good at teaching a user how to think better about a problem, only making them better at phrasing their prompt to get closer to a possible solution<p>* LLMs are stuck in a predictive framework that mandates an answer for the customer, as opposed to a human who is able to say &quot;I don&#x27;t know&quot; and going off to learn more about that thing they&#x27;re stuck on.<p>Ultimately, the tooling is helping novice or entry-level developers and hobbyists write better code, but only because the models were trained on code from more senior or professional developers that was also shared publicly. Senior developers and above may find utility in writing faster code with LLMs, but aren&#x27;t nearly as likely to write better code as a result of the tooling, at least from my subjective reasoning.<p>Now let&#x27;s switch to the business side of things, which I already touched on above. Businesses haven&#x27;t been interested in secure or efficient code until very recently, as we began bumping up against the limits of physical hardware in x86-64 land and lawsuits for failures became more of an existential threat. This means a lot of the code from public samples fits the &quot;done is better than good&quot; mantra of modern business practices, rather than being an improvement to prior releases; even if a business has taken the time to create more secure or efficient code, they likely haven&#x27;t shared it as it&#x27;s a core part of their competitive advantage or product line. This will take years, maybe a decade before the LLM training sets have enough &quot;superior&quot; data to outscore the &quot;inferior&quot; training set data, during which time the status quo - barring a literal revolution in computing - is likely to remain.<p>Admittedly all of this is my subjective POV from infrastructure-world, and could be way off base; YMMV, buyer beware, caveat emptor, etc.
caohongyuan8 months ago
cursor is better
rerdavies8 months ago
Based on my experience, at the present moment in time, I think you should be expecting more code (groundbreaking improvements in productivity), but not necessarily significantly better code. But certainly not worse code. Current generation AIs are writing tactical code absolutely brilliantly (often better than my own code), but often making very odd strategic decisions (functionally decomposing code in odd ways, for example).<p>But, the rate of change in this area is breathtaking. I reasonably expect my AI to improve in the coming months, or even weeks. And I find it difficult to keep up with which AIs are best for generating code at any given moment. There may be AIs that are good at reviewing multi-million-line code bases for security flaws. But I am not currently using one at the present time.<p>What I do know: my AI coding partner this year is writing code that is more accurate and more stylish than any AIs were producing this time last year. The code that&#x27;s being produced is often strategically brilliant -- elegant, concise, only very occasionally using hard-coded constants instead of including the correct headers, and almost completely absent of &quot;hallucinations&quot;. And I&#x27;m using it to regularly generate code in three different languages (C++ for the app server, typescript for the web client, java for the Android client application).<p>I&#x27;ve frequently found myself adopting coding conventions that my AI has shown me. I particularly like<p><pre><code> namespace fs = std::filesystem; </code></pre> And the solution it came up with for writing a std:filebuf implementation stills leaves me speechless. I&#x27;ve done that a few times over my career, and the solution the AI uses is infinitely superior to anything I&#x27;ve ever written -- not something I&#x27;ve EVER seen, but clearly the horrible, never documented way the original authors of the iostream libraries MEANT people to do it, which provides substantial advantages over the way I&#x27;ve been doing it. And absolutely nowhere to be found in the first 30 page of google searches, or among the strangely variously broken and obsolete fragments of code on StackExchange.<p>But my current AI often falls short when it comes to strategic thinking. Functional decomposition is often odd. I often have to refactor code that my AI generates -- sometimes by coaching it through refactoring, and sometimes doing it myself when I move the generated code into production code. But that may change next week. Who knows?<p>Have I used it for debugging existing code? A couple of times. I&#x27;m not currently seeing a huge productivity boost in this area.<p>Today, I coached it to write me a bash shell script to generate a graph of a key development metric using gnuplot. Bash: as a former Windows programmer, bash still terrifies me. Gnuplot: a documentation set that could be called unforgiveable if you were feeling particularly generous. Took me about 20 minutes. &quot;Change the font of the title, please&quot;. &quot;Take input from this program, which produces a column of ISO 8601 dates, and an integer value&quot;. &quot;Rotate the date labels 90 degrees anti-clockwise&quot; (It mistakenly rotated them clockwise. The only flaw in an otherwise fantastic performance). Etc. It took me about 20 minutes to do what would have taken me a couple of hours. I wouldn&#x27;t have done it if I didn&#x27;t have an AI at my disposal.<p>Context: Using Claude 3.5, 40 years of very senior Windows development experience, but only about 3 years of Linux development experience.
black_138 months ago
I work for Boeing and i deal with shitty legacy code and shitty legacy ideas
评论 #41635851 未加载