…and I still don’t get it. I paid for a month of Pro to try it out, and it is consistently and confidently producing subtly broken junk. I had tried doing this before in the past, but gave up because it didn’t work well. I thought that maybe this time it would be far along enough to be useful.
The task was relatively simple, and it involved doing some 3d math. The solutions it generated were almost write every time, but critically broken in subtle ways, and any attempt to fix the problems would either introduce new bugs, or regress with old bugs.
I spent nearly the whole day yesterday going back and forth with it, and felt like I was in a mental fog. It wasn’t until I had a full night’s sleep and reviewed the chat log this morning until I realized how much I was going in circles. I tried prompting a bit more today, but stopped when it kept doing the same crap.
The worst part of this is that, through out all of this, Claude was confidently responding. When I said there was a bug, it would “fix” the bug, and provide a confident explanation of what was wrong… Except it was clearly bullshit because it didn’t work.
I still want to keep an open mind. Is anyone having success with these tools? Is there a special way to prompt it? Would I get better results during certain hours of the day?
For reference, I used Opus 4.6 Extended.
Don’t just use it as a drop in replacement for a programmer; use it to automate menial tasks while employing trust but verify with every output it produces.
A well written CLAUDE.md and prompt to restrict it from auto committing, auto pushing, and auto editing without explicit verification before doing anything will keep everything in your control while also aiding menial maintenance tasks like repetitive sections or user tests.
verify with every output it produces.
I agree that you can get quality output using these tools, but if you actually take the time to validate and fix everything they’ve output then you spend more time than if you’d just written it, rob yourself of experience, and melt glaciers for no reason in the process.
prompt to restrict it from auto committing, auto pushing, and auto editing without explicit verification
Anything in the prompt is a suggestion, not a restriction. You are correct you should restrict those actions, but it must be done outside of the chatbot layer. This is part of the problem with this stuff. People using it don’t understand what it is or how it works at all and are being ridiculously irresponsible.
repetitive sections
Repetitive sections that are logic can be factored down and should be for maintainability. Those that can’t be can be written with tons of methods. A list of words can be expanded into whatever repetitive boilerplate with sed, awk, a python script etc and you’ll know nothing was hallucinated because it was deterministic in the first place.
user tests.
Tests are just as important as the rest of the code and should be given the same amount of attention instead of being treated as fine as long as you check the box.
I agree it’s not perfect; I still only use it very sparingly, I was just just saying as an alternative to trusting everything it does out of the box.
You can’t really just use Claude code raw. You have to give it detailed instructions, use Claude skills,observe results, update prompts. It can be just as consuming, but rather that doing the productive work, you’re just reviewing and correcting AI. People who have success using AI have invested time in their setup and are continuously adjusting it.
I read a lot of these posts that sadly leave out the basic parts: what were your prompts? What does it means in this context ‘vibe coding’? Did you create an initial setup, and slowly build up? Did you left wverything to the agent understanding, and just pushed approve or reject? There are multiple levels of quality that depends on the input. Did you get into context rotting? 3d math means vector math, matrices, or what? Given claude has a serious problem from march at least, the way u use it is paramount. In our team we all use claude with copilot ( sadly, that is a business directive ), and while excpetional at finding small relationships in components and microservices, had to build a long list of skills just to be barely usable in a ‘star trek’ way. The bottom line is that it is that you must be extremely precise when asking. Prompt modeling count a lot. Context build as well. For now, unit tests and data/mocks refactors are working extremely well for me, when i define the tests cases. My agents got to a point where i can safely have small peoperty additions with refactors on multiple repositories at once ( ie: i change the contract on microservice a, microservices b,c,and d are automatically updated ). This last part had to.be built thoug, with memory, engrams, and some fune tuing. It is not always a shit: if not nobody would use it. It is not this revolutionary technology that will make humans obsolete as well ( as they are selling it ).
Key is having it write tests and have it iterate by itself, and also managing context in various ways. It only works on small projects in my experience. And it generates shit code that’s not worth manually working on, so it kind of locks your project in to being always dependent on AI. Being always dependant on AI, and AI hitting a brick wall eventually means you’ll reach a point where you can’t really improve the project anymore. I.e. AI tools are nearly useless.
Don’t jump right in to coding.
Take a feature you want, and use the plan feature to break it down. Give the plan a read. Make sure you have tests covering the files it says it’ll need to touch. If not, add tests (can use LLM for that as well).
Then let the LLM work. Success rates for me are around 80% or higher for medium tasks (30 mins–1 hour for me without LLM, 15–30 mins with one, including code review)
If a task is 5 mins or so, it’s usually a hit or miss (since planning would take longer). For tasks longer than 1 hour or so, it depends. Sometimes the code is full of simple idioms that the LLM can easily crush it. Other times I need to actively break it down into digestible chunks
almost write
Indeed.
It’s not called “correct” coding for a reason.
That’s why people are wrong so often: they feel like something is right, but don’t check. That’s how you get anti -vaxxers, manospere people, MAGA, QAnon, Brexit, etc.
The reason you kept going around in circles and reintroducing bugs you already got rid of is because LLMs don’t remember things. Every time you tell it something it tells it the entire conversation again so it has all the parts. Eventually it runs out of room and starts cutting off the beginning of the convo and now the llm can’t ‘remember’ what it was you were even talking about.
For that you can ask to update a documentation/status file on every update. You can manually add the goal and/or tasks for the future.
With that, I improved my success a lot even when starting new sessions (add in the instructions file to use this file for reference, so you don’t have to remind every time)
producing subtly broken junk
The difference between you and people that say it’s amazing is that you are capable of discerning this reality.
I wonder if it was even able to compile. I am a shitty hobby coder who just does it to make my embedded hardware projects function.
I have yet to get compilable code out of any of the AI bots I have tried. Gemini, mistral, and chatGPT. I am not making an account lol.
I have gotten some compilable python and VBA code for data analysis stuff at work, so I wonder if it is because embedded stuff uses specific SDKs that it can’t handle.
Either way I have given up on it for anything besides bouncing ideas off of or debugging where electromagnetics issues could lie (though it has been completely wrong about that also even though it is using the wrong concepts, it just reminds me of concepts that I might have overlooked)
What I don’t get, though, is how the vibe code bros can’t discern this reality.
How can they sit there and not see that their vibe-coded app just doesn’t do what they wanted it to do? Eventually, you’ve got to try actually running the app, right? And how do you keep drinking the AI kool-aid when you find out that the app doesn’t work?
Vibe code bros aren’t real programmers. They’re business people, not computer people. Even if they have a CS degree, they only got that because they think it’ll get them more money. They lack passion and they don’t care about understanding anything. They probably don’t even care about what they’re generating beyond its potential to be used in a grift.
I graduated college not that long ago and my CS classes had quite a few former business majors. They switched because they think it’ll be more lucrative for them but since they only care about money they didn’t bother to actually learn the material especially since they could just vibe code through everything.
So much this.
After working in tech companies for the last 10 years I’ve noticed the difference between people that “generate code” and those that engineer code.
My worry about the industry is that vibe coding gives the code generators the ability to generate even more code. The engineers (even those that use vibe tools) are not engineering as much code by volume compared to “the generators”.
My hope is that this is one of those “short term gain, long term pain” things that might self correct in a couple of years 🤞.
They’re the same people that copied code from stack overflow that you had to tell them how to actually fix every PR. The difference is the C suite types are backing them this time
Eventually, you’ve got to try actually running the app, right?
At least at my company, no, they just start selling it.
Yes. Exactly. In my experience, there’s more code shops that ship shit than that catch their mistakes.
I do apps that work, i do patches that are production quality. Half the cs world does… I do full stack ai debugging of esp32 projects.
It’s a powerful tool, you just need to learn it’s strong and weak points, just like any other tool you use.
Half the cs world does…
What’s the basis for this claim? I’m doubtful, but don’t have wide data for this.
Rough estimate from my personal connections only. Some work places where ai is not possible, but all that have made an effort report good code. You need to work with what it is - a word generator that sometimes gives correct results. Make it research and not trust training. Never let it do things on its own, require a plan and reason. Make it evaluate its own work/plan.
Most issues i have stem from models beeing too eager. Restrain them and remove the “i can do this next…”behaviour.
Context is king - so proper mcp and documentation that is agent facing. I use serena as i can get lsp for yaml, markup and keep these docs like that
I use my own brain to sketch out what I want to work and how. Before writing any code, I use the LLM to point out gaps and how to close them. Pros and cons of certain decisions. Things you would discuss with colleagues. Then, I come up with a plan for the order I want the code to be written in and how to fragment that into smaller, easy to handle modules. I supervise and review each chunk produced, adapt code mostly manually if required, write the edge case tests - most importantly, run it - and move to the next. This is how I use it successfully and get results much faster than the traditional way.
At my job though I can witness how other people use it. I was asked to review a fully vibecoded fullstack app that contains every mistake possible. Unsanitizised input. Hardcoded tokens. Hardcoded credentials. 2500+ LoC classes and functions. Business logic orchestrators masquerading as service. Full table scans on each request. Cross-tenant data leaks. Loading whole tables into the memory. No test coverage for the most critical paths. Tests requiring external services to run. The list goes on. Now they want me to make it production ready in 8 weeks “because you have AI”.
My point: This was an endorphine fueled vibecoding session by someone who has no experience as developer, asked the LLM to “just make it work”, lacking the ability to supervise the work that comes with experience. It was enough to make it rum locally and pitch a “system engineered w/o any developer” to management.
Those systems need guidance just as a Junior would and I am strongly and loudly advocating to restrict access to this incredibly useful tool to people who know what they do. Nobody would allow a manager to use a laser cutter in a carpentry workshop without proper training, worst case is they will burn down the whole shack.
I appreciate you having a open mind about it at least. I needed some time to adjust as well. I don’t even use Opus, most of the time my workflow consistently produces usable code with Sonnet. Maybe you can try what I explained initially? Just don’t try any language you’re not familiar with, that will not end well.
No, I think you do get it. That’s exactly right. Everything you described is absolutely valid.
Maybe the only piece you’re missing is that “almost right, but critically broken in subtle ways” turns out to actually be more than good enough for many people and many purposes. You’re describing the “success” state.
/s but also not /s because this is the unfortunate reality we live in now. We’re all going to eat slop and sooner or later we’re going to be forced to like it.
“almost right, but critically broken in subtle ways” turns out to actually be more than good enough for many people and many purposes. You’re describing the “success” state.
Exactly. The consequences are at worst a problem for “future me”, and at best “somebody else’s problem”.
AI didn’t create this reality, but it’s certainly moved it into the spotlight and to “center stage.”
Or maybe we will be forced to switch off LLMs and start solving the bugs introduced by their usage using our minds.
As a professional software developer, I truly hope that is the case (and I plan to charge at least 10x my current rate after the AI bubble pops when I’m looking for my next job as I expect there to be a massive shortage of people skilled enough to actually deal with the nightmare spaghetti AI code bases)
Fun times ahead.
It will be interesting (read as: bad) times to get to that point and I agree. The Junior market is basically not existent ever since coding agents appeared, stripping the industry of its future Seniors. We will be chained to our desks.
You and me both. We will be the next version of the COBOL Cowboys.
Have you been coding professionally long?
I find that the only time I can use these chatbots for a task I really need to already know what i’m doing so that I can read the output and fix the issues. This is like having junior devs on your team and being a code reviewer more than being a full time coder. They get a lot of things wrong but there’s so much usable that you can save a ton of time over doing everything yourself from scratch.
Just like with junior devs, you can send them back to fix what you know is wrong and give them feedback to improve various things you would prefer done another way. There’s no emotions though, so you can just be blunt and concise with feedback.
They get a lot of things wrong but there’s so much usable that you can save a ton of time over doing everything yourself from scratch.
Your experience with Junior devs has been quite different from mine.
I work with Junior devs because someday they will be senior devs who owe me a favon, even though they’ve always only costed me time.
Edit: I also work with junior devs because sometimes a tiny corner of my job is both mind-numbingly boring, and also weirdly difficult to automate away.
I assign that work to junior devs because I don’t want to do it.
In doing so, I am wasting the boss’s money, since I could do it faster.
But I consider it but just another part of the price of hiring me, because it keeps me happy.
Nice comparison, but the bugs created by junior software developers are usually much easier to find than the bugs created by LLMs.
Vibe coding, in the sense of telling the model to make codebase changes, then directly using the output produced, is 100% marketing bullshit that does not scale beyond toy examples.
Here’s the rub: Claude is extremely useful as an advanced autocomplete, if and only if you’re guiding it architecturally through every task it runs, and you vet + revise the output yourself between iterations. You cannot effectively pilot entirely from chat in a mature codebase, and you must compile robust documentation and instructions for Claude to know how to work with your codebase.
You also must aggressively manage information in the context window yourself and keep it clean. You mentioned going in circles trying to get the robot to correct itself: huge mistake. Rewind to before the error, and give it better instructions to steer it away from the pitfall it fell into. Same vein, you also need to reset ASAP after pushing into the >100k token mark, because the models start melting into putty soon after (yes, even the “extended” 1M-window ones).
I’m someone who has massively benefited from using modern LLMs in my work, but I’m also a massive hater at the same time: They’re just a tool, not magic, and have to be used with great care and attention to get reasonable results. You absolutely cannot delegate your thinking to them, because it will bite you, hard and fast.
For your use case (3D math), what I recommend is decomposing your end goal into a series of pure functions that you’ll string together. Once you have that list, that’s where Claude comes in. Have it stub those functions for you, then have it implement them one at a time, reviewing the output of every one before proceeding.
My preferred way of using LLM coders is:
- plan only
- read the spec file I just wrote
- optionally ask me questions in ‘qa.md’, I’ll reply inline Repeat until it stops asking me questions, then switch to a different model and ask again. I usually use both gpt5.3-codex AND Claude Sonnet
Then I have it update the spec. I start a new session to have it implement. Finally review the code. If I don’t like it, undo and revisit the spec. Usually it’s because I’m trying to do too much at once. And I need to break it down into multiple specs.
Adversarial reviews are also great ways to prune bad ideas and assumptions from plans. Have helped me out greatly and made the better LLMs often go “plan said do X, but doing that is a unknown huge risk that may take longer then the rest of the plan”.
The superpowers plugin does the brainstorm, qa, design plan, implementation plan, implement, review quite well. It should aid the process of actually doing feature type work. I also add adversarial reviews into the process, saves a lot of time debugging what went wrong after implementation.
This is the most pragmatic take I’ve read and it resonates strongly with my own experience. Claude can be a very useful tool, but like any other there is a learning curve and often many sharp edges. I’ve had Claude build some reasonably complex code bases, but it takes work. Its pretty decent at “coding” but pretty terrible at the rest of software engineering.
-
Did you have MCP tooling setup so it can get lsp feedback? This helps a lot with code quality as it’ll see warnings/hints/suggestions from the lsp
-
Unit tests. Unit tests. Unit tests. Unit tests.
I cannot stress enough how much less stupid LLMs get when they jave proper solid Unit tests to run themselves and compare expected vs actual outcomes.
Instead of reasoning out “it should do this” they can just run the damn test and find out.
They’ll iterate on it til it actually works and then you can look at it and confirm if its good or not.
I use Sonnet 4.5 / 4.6 extensively and, yes, its prone to getting the answer almost right but a wrong in the end.
But the unit tests catch this, and it corrects.
Example: I am working on my own fame engine with monogame and its about 95% vibe coded.
This transform math is almost 100% vibe coded: https://github.com/SteffenBlake/Atomic.Net/blob/main/MonoGame/Atomic.Net.MonoGame/Transform/TransformRegistry.cs
The reason its solid is because of this: https://github.com/SteffenBlake/Atomic.Net/blob/main/MonoGame/Atomic.Net.MonoGame.Tests/Transform/Integrations/TransformRegistryIntegrationTests.cs
Also vibe coded and then sanity checked by me by hand to confirm the math checks out for the tests.
And yes, it caught multiple bugs, but the agent automatically could respond to that, fix the bug, rerun the tests, and iterate til everything was solid.
Test Driven Development is huge for making agents self police their own code.
-
.net runtime after 10 months of using and measuring where LLMs (including latest Claude models) shine reported a mindboggling success rate peaking at 75% (sic!) for changes of 1-50 LOC size - and it’s for an agentic model (so you give it a prompt, context, etc, and it can run the codebase, compile it, add tests, reason, repeat from any step, etc etc).
Except it was clearly bullshit because it didn’t work.
Welcome to the LLMs where everything is hallucinated and correctness doesn’t matter.
Is anyone having success with these tools
Define success.
Is there a special way to prompt it?
It gets better the more you use it, you will learn what works for you, and what does not. Right now the hot shit is “autonomous agent swarms” peddled by the token sellers as a way to output correct massive features. Do not touch that for now.
What helps with Claude / llms 101:
-
when it tells you something about an API, using a tool or whatever, tell it tool version and order it to give you documentation page proving the solution is possible.
-
when it oneshots a working solution you will get a dopamine hit. Be aware of that, as it can be addictive or make you trust it. Do not trust it, it sucks long term.
-
it will alwyas default to below average solution. Know where your hotspots are, and be extra judgy there.
-
it will get lazy and lie to you, especially with tests
-
it will not propose code refactors on its own.
-
despite the token peddlers claims, no matter if your using the 1M token context window model, the shit degrades when the context window is over 20k-30k tokens - so switch context windows often for better outcomes, but that means you will be burning more money - which obviously benefits the token peddlers.
-
do not trust the hype - so far any and all tall claim of a breakthrough from the token peddlers were a lie (e.g. vibing working os that can run Doom, vibing a next.js 96% replacement in a week, vibing a browser, compiler, vibing a browser jailbreak via Mythos)
Would I get better results during certain hours of the day?
Afaik USA timezone has worse performance.
.net runtime after 10 months of using and measuring where LLMs (including latest Claude models) shine reported a mindboggling success rate peaking at 75% (sic!) for changes of 1-50 LOC size - and it’s for an agentic model (so you give it a prompt, context, etc, and it can run the codebase, compile it, add tests, reason, repeat from any step, etc etc).
I assume this is from https://devblogs.microsoft.com/dotnet/ten-months-with-cca-in-dotnet-runtime/?
You assume correctly.
-
