“No Duh,” say senior developers everywhere.
The article explains that vibe code often is close, but not quite, functional, requiring developers to go in and find where the problems are - resulting in a net slowdown of development rather than productivity gains.
I work adjacent to software developers, and I have been hearing a lot of the same sentiments. What I don’t understand, though, is the magnitude of this bubble then.
Typically, bubbles seem to form around some new market phenomenon or technology that threatens to upset the old paradigm and usher in a new boom. Those market phenomena then eventually take their place in the world based on their real value, which is nowhere near the level of the hype, but still substantial.
In this case, I am struggling to find examples of the real benefits of a lot of these AI assistant technologies. I know that there are a lot of successes in the AI realm, but not a single one I know of involves an LLM.
So, I guess my question is, “What specific LLM tools are generating profits or productivity at a substantial level well exceeding their operating costs?” If there really are none, or if the gains are only incremental, then my question becomes an incredulous, “Is this biggest in history tech bubble really composed entirely of unfounded hype?”
AI is a financial scam. Basically companies that are already mature promise great future profits thanks to this new technological miracle, which makes their stock more valuable than it otherwise would be. Cory Doctorow has written eloquently about this.
From what I’ve seen and heard, there are a few factors to this.
One is that the tech industry right now is built on venture capital. In order to survive, they need to act like they’re at the forefront of the Next Big Thing in order to keep bringing investment money in.
Another is that LLMs are uniquely suited to extending the honeymoon period.
The initial impression you get from an LLM chatbot is significant. This is a chatbot that actually talks like a person. A VC mogul sitting down to have a conversation with ChatGPT, when it was new, was a mind-blowing experience. This is a computer program that, at first blush, appears to be able to do most things humans can do, as long as those things primarily consist of reading things and typing things out - which a VC, and mid/upper management, does a lot of. This gives the impression that AI is capable of automating a lot of things that previously needed a live, thinking person - which means a lot of savings for companies who can shed expensive knowledge workers.
The problem is that the limits of LLMs are STILL poorly understood by most people. Despite constructing huge data centers and gobbling up vast amounts of electricity, LLMs still are bad at actually being reliable. This makes LLMs worse at practically any knowledge work than the lowest, greenest intern - because at least the intern can be taught to say they don’t know something instead of feeding you BS.
It was also assumed that bigger, hungrier LLMs would provide better results. Although they do, the gains are getting harder and harder to reach. There needs to be an efficiency breakthrough (and a training breakthrough) before the wonderful world of AI can actually come to pass because as it stands, prompts are still getting more expensive to run for higher-quality results. It took a while to make that discovery, so the hype train was able to continue to build steam for the last couple years.
Now, tech companies are doing their level best to hide these shortcomings from their customers (and possibly even themselves). The longer they keep the wool over everyone’s eyes, the more money continues to roll in. So, the bubble keeps building.
When the AI bubble bursts, even janitors and nurses will lose their jobs. Financial institutions will go bust.
I have never seen an AI generated code which is correct. Not once. I’ve certainly seen it broadly correct and used it for the gist of something. But normally it fucks something up - imports, dependencies, logic, API calls, or a combination of all them.
I sure as hell wouldn’t trust to use it without reviewing it thoroughly. And anyone stupid enough to use it blindly through “vibe” programming deserves everything they get. And most likely that will be a massive bill and code which is horribly broken in some serious and subtle way.
I’ve seen and used AI for snippets of code and it’s pretty decent at that.
With my colleagues I always compare it to a battery powered drill. It’s very powerful and can make shit a lot easier. But you’d not try to build furniture from scratch with only a battery powered drill.
You need the knowledge to use it - and also saws, screws, the proper bits for those screws and so on and so forth.
Eh I had it write a program that finds my PCs ip and sends it to the Unifi gateway to change a rule. Worked fine but I guess technically it is mostly using the go libraries written by someone else.
How is it not correct if the code successfully does the very thing that was prompted?
F.ex. in my company we don’t have any real programmers but have built handful of useful tools (approx. 400-1600 LOC, mainly Python) to do some data analysis, regex stuff to cleanup some output files, index some files and analyze/check their contents for certain mistakes, dashboards to display certain data, etc.
Of course the apps may not have been perfect after the very first prompt, or even compiled, but after iterating an error or two, and explaining an edge case or two, they’ve started to perform flawlessly, saving tons of work hours per week. So how is this not useful? If the code creates results that are correct, doesn’t that make the app itself technically ”correct” too, albeit likely not nearly as optimized as equivalent human code would be.
If the code doesn’t compile, or is badly mangled, or uses the wrong APIs / imports or forgets something really important then it’s broken. I can use AI to inform my opinion and sometimes makes use of what it outputs but critically I know how to program and I know how to spot good and bad code.
I can’t speak for how you use it, but if you don’t have any real programmers and you’re iterating until something works then you could be producing junk and not know it. Maybe it doesn’t matter in your case if its a bunch for throwaway scripts and helpers but if you have actual code in production where money, lives, reputation, safety or security are at risk then it absolutely does.
It’s not bad for your use case but going beyond that without issues and actual developpers to fix the vibe code is not yet possible for llms
Of course. Shareholders want results, and not just results for nVidia’s bottom line.
The people talking about AI coding the most at my job are architects and it drives me insane.
I am a software architect, an mainly usw it to refactor my own old code… But i am maybe not a typical architect…
I don’t really care if people use it, it’s more that it feels like a quarter of our architect meeting presentations are about something AI related. It’s just exhausting.
i use it for programming arduinos for my smarthome. its pretty nice but also aggravating.
So when the AI bubble burst, will there be coding jobs available to clean up the mess?
There already are. People all over LinkedIn are changing their titles to “AI Code Cleanup Specialist”.
I mean largely for most of us I hope. But I feel like the tech sector was oversatured because of all the hype of it being an easy get rich quick job. Which for some people it was.
According to Deutsche Bank the AI bubble is
athe pillar of our economy now.So when it pops. I guess that’s kinda apocalyptic.
Edit - strikethrough
Only for taxpayers ☝️
Writing apps with AI seems pretty cooked. But I’ve had some great successes using GitHub copilot for some annoying scripting work.
I think it’s useful for writing mundane snippets I’ve written a million times or helping me with languages I’m less familiar with, but anything more compex becomes pretty spaghetti pretty quick.
AI is works well for mindless tasks. Data formatting, rough drafts, etc.
Once a task requires context and abstract thinking, AI can’t handle it.
Eh, I don’t know. As long as you can break it down into smaller sub-tasks, AI can do some complex stuff. Just have to figure out where the line is. I’ve nudged it along into reading multiple LENGTHY API documentation pages and written some fairly complex scripting logic.
I’d much rather write my own bugs to have to waste hours fixing, thanks.
deleted by creator
I code with LLMs every day as a senior developer but agents are mostly a big lie. LLMs are great for information index and rubber duck chats which already is incredible feaute of the century but agents are fundamentally bad. Even for Python they are intern-level bad. I was just trying the new Claude and instead of using Python’s pathlib.Path it reinvented its own file system path utils and pathlib is not even some new Python feature - it has been de facto way to manage paths for at least 3 years now.
That being said when prompted in great detail with exact instructions agents can be useful but thats not what being sold here.
After so many iterations it seems like agents need a fundamental breakthrough in AI tech is still needed as diminishing returns is going hard now.
If it wasn’t for all the AI hype that it’s going to do everyone’s job, LLMs would be widely considered an amazing advancement in computer-human interaction and human assistance. They are so much better than using a search engine to parse web forums and stack overflow, but that’s not going to pay for investing hundreds of billions into building them out. My experience is like yours - I use AI chat as a huge information index mainly, and helpful sounding board occasionally, but it isn’t much good beyond that.
I will concur with the whole ‘llm keeps suggesting to reinvent the wheel’
And poorly. Not only did it not use a pretty basic standard library to do something, it’s implementation is generally crap. For example it offered up a solution that was hard coded to IPv4, and the context was very ipv6 heavy
I have a theory that it’s partly because a bunch of older StackOverflow answers have more votes than newer ones using new features. More referring to not using relatively new features as much as it should.
I’d wager that the votes are irrelevant. Stock overflow is generously <50% good code and is mostly people saying ‘this code doesn’t work – why?’ and that is the corpus these models were trained on.
I’ve yet to see something like a vibe coding livestream where something got done. I can only find a lot of ‘tutorials’ that tell how to set up tools. Anyone want to provide one?
I could… possibly… imagine a place where someone took quality code from a variety of sources and generate a model that was specific to a single language, and that model was able to generate good code, but I don’t think we have that.
Vibe coders: Even if your code works and seems to be a success, do you know why it works, how it works? Does it handle edge cases you didn’t include in your prompt? Does it expose the database to someone smarter than the LLM? Does it grant an attacker access to the computer it’s running on, if they are smarter than the LLM? Have you asked your LLM how many 'r’s are in strawberry?
At the very least, we will have a cyber-security crisis due to vibe coding; especially since there seems to be a high likelihood of HR and Finance vibe coders who think they can do the traditional IT/Dev work without understanding what they are doing and how to do it safely.
Oh yes. The Great
pathlib. The Blessedpathlib. Hallowed be it and all it does.I’m a Ruby girl. A couple of years ago I was super worried about my decision to finally start learning Python seriously. But once I ran into
pathlib, I knew for sure that everything will be fine. Take an everyday headache problem. Solve it forever. Boom. This is how standard libraries should be designed.Pathlib is very nice indeed, but I can understand why a lot of languages don’t do similar things. There are major challenges implementing something like that. Cross-platform functionality is a big one, for example. File permissions between Unix systems and Windows do not map perfectly from one system to another which can be a maintenance burden.
But I do agree. As a user, it feels great to have. And yes, also in general, the things Python does with its standard library are definitely the way things should be done, from a user’s point of view at least.
I disagree. Take a routine problem and invent a new language for it. Then split it into various incompatible dialects, and make sure in all cases it requires computing power that no one really has.
https://www.youtube.com/watch?v=VsE0BwQ3l8U&t=1492s
And the band plays on
LLMs work great to ask about tons of documentation and learn more about high-level concepts. It’s a good search engine.
The code they produce have basically always disappointed me.
On proprietary products, they are awful. So many hallucinations that waste hours. A manager used one on a code review of mine and only admitted it after I spent the afternoon chasing it.
Those happen so often. I’ve taken to stop calling them hallucinations anymore (that’s anthropomorphising and over-selling what LLMs do imho). They are statistical prediction machines, and either they hit their practical limits of predicting useful output, or we just call it broken.
I think the next 10 years are going to be all about learning what LLMs are actually good for, and what they are fundamentally limited at no matter how much GPU ram we throw at it.
Not even proprietary, just niche things. In other words anything that’s rarely used in open source code, because there’s nothing to train the models on.
I sometimes get up to five lines of viable code. Then upon occasion what should have been a one liner tries to vomit all over my codebase. The best feature about AI enabled IDE is the button to decline the mess that was just inflicted.
In the past week I had two cases I thought would be “vibe coding” fodder, blazingly obvious just tedious. One time it just totally screwed up and I had to scrap it all. The other one generated about 4 functions in one go and was salvageable, though still off in weird ways. One of those was functional, just nonsensical. It had a function to check whether a certain condition was present or not, but instead of returning a boolean, it passed a pointer to a string and set the string to “” to indicate false… So damn bizarre, hard to follow and needlessly more lines of code, which is another theme of LLM generated code.
AI coding is the stupidest thing I’ve seen since someone decided it was a good idea to measure the code by the amount of lines written.
More code is better, obviously! Why else would a website to see a restaurant menu be 80Mb? It’s all that good, excellent code.
I would say absolutely in the general sense nost people, and the salesmen, frame them in.
When I was invited to assist with the GDC development, I got a chance to partner with a few AI developers and see the development process firsthand, try my hand at it myself, and get my hands on a few low parameter models for my own personal use. It’s really interesting just how capable some models are in their specific use-cases. However, even high param. models easily become useless at the drop of a hat.
I found the best case, one that’s rarely done mind you, is integrate the model into a program that has the ability to call a known database. With a properly trained model to format output in both natural language and use a given database for context calls, and concrete information, the qualitative performance leaps ahead by bounds. Problem is, that requires so much customization it pretty much ends up being something a capable hobbyist would do, it’s just not economically sound for a business to adopt.
