I've been playing with it on weekends for the last few months. 9 out of 10 projects, it's failed.
Projects as simple as "set up a tmux/vim binding so I can write prompts in one pane and run claude in the other". Fails.
I've been coding for over 20 years.
If there is no learning curve, why doesn't it work for me? You can't say I'm not using it right, because if that was true, then all I need to do is climb the learning curve to fix that, the curve that you say doesn't exist.
It doesn't work if you're treating it like a peer engineer. It only works if you treat it like you're a customer with no concern with how it works behind the scenes.
That's what's being asked of me in my last two jobs. Vibe code it, if it's bad just throw it away and regenerate it because it's "cheap". The only thing that matters is that you can quickly generate visible changes and ship it to market.
Out of frustration I asked upper management (in my current job), if you want me to use AI like that then I'll do it. But when it inevitably fails, who is responsible? If there's no risk to me, I will AI generate everything starting today, but if I have to take on the risk I won't be able to do this.
Their response was that AI generates the code, I'm responsible for reviewing it and making sure it's risk free. I can see that they're already looking for contractors (with no skin in the game) that are more than willing to run the AI agents and ship vibe code, so I'm at a loss on what to do.
I've used Claude Code to do everything from vibe-code personal apps including a terminal on top of libghostty to building my perfect desktop environment on NixOS (I'd never used Nix until then).
I'm not sure why it isn't working for you. Maybe your expectation is a perfect one-shot or else it has zero value, and nothing in between?
But my advice is to switch gears and see the "plan file" as the deliverable that you're polishing over implementation. It's planning and research and specification that tends to be the hard part, not yoloing solutions live to see if they'll work -- we do the latter all the time to avoid 10min of planning.
So, try brainstorming the issue with Claude Code, talk it through so it's on the same page as you, ensure it's done research (web search, docs) to weigh the best solutions, and then enter plan mode so it generates a markdown plan file.
From there you can read/review,tweak the plan file. Or have it implement it. Or you implement it. But the idea is that an LLM is useful at this intermediate planning stage without tacking on additional responsibilities.
I think by "no learning curve" they are referring to how you can get value from it without doing the research you'd need to use a conventional tool. But there is a learning curve to getting better results.
I learned my plan file workflow just from Claude Code having "Plan Mode" that spits out a plan file, and it was obvious to me from there, but there are people who don't know it exists nor what the value of it is, yet it's the centerpiece of my workflow. I also think it's the right way to use AI: the plan/prompt is the thing you're building and polishing, not skipping past it to an underspecified implementation. Because once you're done with the plan, then the impl is trivial and repeatable from that plan, even if you wanted to do the impl yourself.
I'm way past the point of arguing anything here, just trying to help.
> So, try brainstorming the issue with Claude Code, talk it through so it's on the same page as you, ensure it's done research (web search, docs) to weigh the best solutions, and then enter plan mode so it generates a markdown plan file.
From there you can read/review,tweak the plan file. Or have it implement it. Or you implement it.
This is exactly the workflow that works very well for me in Cursor (although I don't use their Plan Mode - I do my version of it). If you know the codebase well this can increase your speed/productivity quite a bit. Not trying to convince naysayers of this, their minds are already made up. Just wanted to chime in that this workflow does actually work very well (been using it for over 6 months).
The first time I saw something like this in action was in a video about agentic blabla features in VS Code on the official VS Code YouTube channel. Pretty much write a complete and detailed specification, fire away and hope for the best. The workflow kinda clicked for me then but I still find a hard time adjusting to this potential new reality where slowly it won't make sense to generally write code "by hand" and only intervene to make pinpoint changes after reviewing a lot of code.
I've been reading a book about the history of math and at some points in the beginning the author pointed out how some fields undergo a radical change within due to some discovery (e.g. quantum theory in physics) and the practitioners in that field inevitably go through this transformation where the generations before and after can't really relate to each other anymore. I'm paraphrasing quite a bit though so I'll just recommend people check out the book if they're interested: The History of Mathematics by Jacqueline Stedall
I haven't written code by hand since December when Claude Opus 4.5 came out. It was clear that the inflection point arrived where it's at least as good as I am at implementing a plan. But not only that: it had good ideas like making impossible states impossible with a smart union type without being told and without me deeply modeling the domain in my head to derive a system invariant I could encode like that.
It was depressing watching all of this unfold over the last few years, but now I'm taking on more projects and delivering more features/value than ever before. That was the reason I got into software anyways, to make good software that people like to use.
> the generations before and after can't really relate to each other anymore
Yeah, good point. In some ways it's already crazy to me that we used to write code by hand. Especially all the chore work, like migrating/refactoring, that's trivial for even a dumb LLM to do. It kinda feels like a liability now when I'm writing code, kinda like how it feels when the syntax highlighting or type-checker breaks in the editor and isn't giving you live feedback, so you're surprised when it compiles and runs on the first try.
I remember having a hard time imagining what it was like for my dad to stub out his software program on paper until his scheduled appointment with the university punch card machine. And then sure being happy that I could just click a Run button in my editor to run my program.
Correction one week later: the book I was talking about is A History of Mathematics by Luke Hodgkin not the one I mentioned in my parent comment. I apologize for mixing them up.
Did it not work after the first try and you gave up? Did it not produce any usable code that you could hand tweak or build off of? I want to understand your definition of "failed" here.
What's your definition of "working"? Do you consider it working, when you have to put more effort into prompting back-and-forth than writing it the old way?
I honestly think the people who love Claude were not super proficient coders. That's the only thing I can think of to explain why writing gobs of English and then code reviewing in a loop could be easier than just coding yourself.
The commenter you replied to seems to be oblivious to the fact that this act, described in the article, is merely a consequence of the war they started.
Iranian hackers have been at place for quite some time beforehand.
And it's not a war started, its a "war" responding to decades of heinous, vicious, deadly funding of terrorist organizations, and bombing of innocent civilians.
Defending Iran is akin to defending a serial murderer. Or complaining that the serial murdered got shot while resisting arrest. Ridiculous.
I sincerely hope the decent people of Iran do get rid of this ridiculous, religiously ran and controlled state.
The US killed many, many more civilians accross the world that Iran ever did. Yet you don't seem to care about that, why?
> And it's not a war started, its a "war" responding to decades of heinous, vicious, deadly funding of terrorist organizations, and bombing of innocent civilians.
As if the US hadn't been antagonizing Iran for decades. Trump broke the nuclear agreements (which Iran had been following), then refused to negotiate new ones, then joined Israel in their bloodlust for muslim blood. This war is aimless, and only serves to radicalize the Iranian people against Israel and the US. Which will inevitably result in even more bloodshed down the line.
> Trump broke the nuclear agreements (which Iran had been following), then refused to negotiate new ones
This is the most head-slapping part of this whole situation. We had a nuclear deal and he pulled the US out of it for no good reason (my read: because he just hates Obama that much that anything he did he wanted to undo). This situation is 100% on this president.
I don't see why this matters, there are accidental civilian casualties in every war. This was unintentional, unlike Iran killing 30,000 of their own citizens, which was entirely deliberate.
If you can find evidence the United States directly targeted a school with the intent of killing children and not just due to outdated intel (and somebody setting up a school in what was once part of an Iranian Revolutionary Guard naval base), maybe I'd change my mind.
30000 is nothing compared to the civilians the US has killed all over the world, all "accidentally" of course. Since 2023 Israel has killed 57000 civilians in Gaza. Shouldn't you be calling for an invasion of Israel on humanitarian grounds then?
I'm not quite getting your point. Are you saying that when Iran kills children, we should get angry and bomb them, and when the US kills children, other countries shouldn't get angry and bomb the US?
There absolutely is a comparison. Both acts are evil. Just because Iran's regime has a history of even more heinous evil acts doesn't absolve the United States and Israel of their own evil acts.
So, since the Iranian regime killed protesters, it's OK for the US regime to obliterate a girl's school? And then lie about it? I'm having trouble following your reasoning.
Tell me again why was this war necessary for the US? What sort of threat did Iran pose? Wasn't their nuclear program "obliterated" when we bombed them last year? Every time someone from the Trump administration talks, it's a different reason.
Hey, so what you are saying is that unless we use the AI that we control, to take control of the mass surveillance and autonomous drone strike systems, you will force us to take control of these systems?
I mean, did H just Open Clawed the entire US military?
And what I'm wondering is why SecDev H thinks that forcing Anthropic to integrate their AI with the country's mass surveillance and autonomous drone strike technology is a winning move for him.
"Ok, if you don't do what I tell you then you HAVE to connect the autonomous AI engine that only you understand and control, I repeat you HAVE to connect your golem to my control systems."
Like a bank robber threatening to hand the gun to the teller if they don't put the money in the bag.
Like SecDev H "open claw"-ing the entire US military.
well, how about "abortion legal" to "abortion murder"... possible to see this coming, but I know doctors in NY who are now afraid to travel to Texas.
How about DEI initiatives as good things in 2024 and a mark of evil in 2025? Lots of people were fired because in 2024 their boss told them to work on DEI and they did what their boss told them to do. Turns out this was a capital offense.
I am not commenting on your specific example of DEI but I want to make the general point that you are always responsible for what you do, irregardless of whether you were told to do it by your boss, or commanding officer, or whatever.
So again, I don't care about the specific example you used but if something is 'in fashion' and you go along with it, including at work, then you are ultimately responsible for that choice. Because it is always a choice, including being a hard choice that results in you losing your job.
But working on DEI on your boss' orders in 2024 wasn't reprobable, anymore than bringing your boss a cup of coffee to their desk was.
The point is that the shift in what is considered "a capital crime" is arbitrary, this is not the Nuremberg trials. You cannot protect yourself by being a decent person, whatever you do today can be a crime tomorrow, and AI can assist those looking for your flaws.
Projects as simple as "set up a tmux/vim binding so I can write prompts in one pane and run claude in the other". Fails.
I've been coding for over 20 years.
If there is no learning curve, why doesn't it work for me? You can't say I'm not using it right, because if that was true, then all I need to do is climb the learning curve to fix that, the curve that you say doesn't exist.
reply