Where's the Shovelware? Why AI Coding Claims Don't Add Up
78% of developers claim AI makes them more productive. 14% say it's a 10x improvement. So where's the flood of new software? Turns out those productivity claims are bullshit.
You're viewing a single thread.
I dont get to decide what i code at work. My manager and product owners decide based on business needs. Most of the time its fixes and adding or removing functions as competing interests change priorities. But its really good at documenting old code while everyone figures exactly what they want. This author is in the 80s asking why every company doesnt immediately have a website now that the internet is available.
until the ’90s*
Thank you for the correction!
np bb
That's unfortunate for you, but not every company operates like that. There's new startups every day, and with all the VC money they're getting, they're in a prime position to be building these new products. The fact so many AI products are under-delivering is enough of an indicator for me to agree with the article's logic
Your response seems very enterprise-focused. I think you might be missing the kind of software development that happens before it becomes enterprise. All of these metrics are very reasonable for new products, startups, consulting, and hobby hackers. If code were moving 10X now, we should reasonably see 10X new growth. These numbers show we’re not.
Arguably we should also see a 10X something in legacy and enterprise as well which is harder to measure. If we assume a 10X dev is producing 10X more code, we should expect 10X more bugs so we should also see a rise in QA positions. We’re not, so that’s a good indicator. We should also see a rise in product manager roles to handle teams that are suddenly producing 10X per member. We’re not, so that’s a good indicator. We should also see 10X new product deliveries from companies like Salesforce. We’re not, so that’s a good indicator.
You completely missed the sections on how long these tools have been available. Your point about the internet would be valid if this article was written in, say, 2021 when Copilot and Tabnine were new and hot. It would also have maybe been valid in early 2023 when people were first spinning up workflows off ChatGPT and making 10X promises. It’s now years later and we’re not seeing any growth in any of those numbers as illustrated by the article.
I did my time in start ups and VCs. Its not all that much different. They have a main product and you spend your timevenhancing or integrating that with everyone else. Its just getting started. Were in the bbs era of ai. Most people are still just trying out copilot. Go watch the machiners and creators on youtube or one of the other platforms. Its working it way into everything and still being refined. People pay way to much attention to hype and propoganda/advertising. Just like with tesla but electric cars are still going strong, getting better and increasingly replacing ice cars. Just because front men overhype things dont mean theyre without value. Like ive said in other comments ai as it is now is a tool like any other. There will be fhose that adapt and those that fall behind. This is all just deja vu for me with soalr power and electric cars from from the 80s and 90s. Theyll never be efficient enough, theyll never have the range, theyll take up to much space, be too heavy, wear out to fast, etc etc.
