Around 2 years ago I had to clean up a mess because someone who doesn't really know what they're doing designed an instancing system for a game. They heavily used AI to design every part of it and it was awful. Data corruption, performance problems, lost items, race conditions everything you can think of was an issue. It took me 2 weeks just to get it to an "acceptable" level and it was still awful as the whole design was simply flawed.
Fast forward to today: different company, same person, SAME issues with an AI that is 'allegedly' much better than it was. This time I only heard about these issues and wasn't the one who had to deal with it so I just had a really good laugh.
AI is only as good as the person using it, that's why we have such vast range of what people "claim" AI can do and why everyone has way different opinions of it.
If you need someone to tell you how stupid your ideas are, either learn to ask in a way that invites criticisms, or hire a senior engineer. Don't try to influence LLM makers to make AI less deferential. That's the worst possible direction to go
It also makes it an incredible tool for manipulation.
It took some effort, and I agree that there very likely are those who will not learn to selectively disengage this innate behaviour. That's why you should pay me a ton of cash each month instead of using Claude directly ;)
Bingo. Hi that’s me.
I’ve been trying to teach people how to use LLMs effectively not just dump shit in them but actually talk to them like you would expect a computer to understand and it totally breaks peoples brains
I’m quite successful in helping people get somewhere usable that they weren’t…but to get to the point of fluency with computing systems, and I would argue this is prior to LLMs as well, where you can actually get what you want more reliably out of a computing interaction than you can with a human interaction, is an entirely different way of thinking
That mode of thinking is just generally not accessible to the vast majority of humans. Not because there’s something wrong with them
but it takes somebody who can hold both extremely large scale problems and very very granular specific implementation problems in your head all at once and that is a rare skill.
This describes the entire software engineering profession to me.
We have come up with all sorts of devices to make this go more smoothly, or to enable us to focus on specific sub-parts as long as possible.
That said, at some point (both in design and integration), you need vision and attention to detail to make progress. The skill seems learnable to me, but watching others struggle sometimes makes me wonder.
One reaction to this might be "well that's not what I mean, that suggests you're prompting with too much directionality" which could further be condensed to "you're prompting wrong". The trouble with this is that _even when I am trying to be extremely precise and avoid biasing the result_, I still will see the output and go "ah shit, I can see it 'aligning' with whatever dumb thing I've just said as if it is a good/plausible direction".
At that point it starts to feel like the prompt is more dice roll than skill at times, which makes me feel like I'm operating a fancy knowledge slot machine.
And from there it's a interactive discussion drilling down on details until I understand the problem and the solutions better.
It definitely challenges my bias when I do this. The one thing it doesn't challenge is the X. Formulate the problem poorly, and you'll get a bad solution. Or rather, you'll end up with a good solution to the wrong problem. Which is even worse than a bad solution to the right problem.
Which is largely why I'm not at all worried about losing my job to AI. It takes some experience to formulate the problem correctly. I don't feel like I'm made redundant by AI, I'm just way faster than I used to be, my thinking is more abstract.
A good prompt I'll often use is "is there a industry standard solution that is applicable to this problem?" You very rarely want novel solutions. Don't reinvent the wheel just because AI lets you do it 10x as fast. Use a wheel. They're round for a reason.
Sometimes I find it useful to discuss things with a different model. I like Gemini for discussion and Claude for implementation. With Gemini I go about it as a learning session, discussing options and details. I honestly think this is mostly because it compartmentalizes the phases in a natural way for me. One interface for brainstorming and learning, and another for planning and implementing.
Sorry this comment turned into a rather disorganised collection of ramblings, I hope you can extract some kernel of usefulness from it all.
I don't think that is the flip side. That's just obviously bad. Everything that is obviously bad, the model makers will also ~notice and work to make better. They seem to be a competent and attentive bunch, on the whole.
Suggesting it should be 'subservient' is also anthropomorphizing. I think your callout is correct, but you still can't help but refer to it in terms we use for other people or living entities. This is by design from the AI companies.
Not really, you can program a machine to give out orders humans can interpret, so humans can serve a machine that isn't anthropomorphized.
A hammer isn’t subservient, it doesn’t have the capacity to be. Saying a hammer is subservient is stretching the definition for literary flourish, but it doesn’t actually make a lot of sense.
The definition that came up for subservient when I checked was “prepared to obey others unquestioningly“.
I don't think an inanimate object is capable of "obeying." Or at least that is a very strange way to refer to the act of using a tool.
They’re not communicating, you’re just being observant.
It doesn’t. Computer interfaces had no superfluous subservient text for their entire history prior to LLMs. Some of these interfaces have been highly efficient as tools, arguably more efficient than more recent software in many cases.
When people complain about LLMs being subservient, they’re not complaining about the tool fulfilling their request. They’re complaining about being forced to read a lot of superfluous, overly polite, or even self-deprecating language. There’s nothing in the entire history of tools (going back to Neolithic times) that would indicate that we need that. All of that stuff is an artifact of social interaction between humans in the presence of cultural norms.
When you’re alone in your shop with your tools, you don’t need your bandsaw to apologize to you for nicking your finger.
Clippy would like to help you correct this statement.
Fun experiment, chat with an LLM and swap roles. Tell it you're gonna be the assistant and them the assisted. I found they're pretty bad at using a human for what they're good for.
Most of the conversational skill and perceived intelligence of these models in hidden in RL/system prompts.
I suddenly have new concerns about what my future might be like.
And it does get people into a lot of trouble.
I have got into trouble with it when it is extremely confident about something I am not very familiar with (as recently as two weeks ago with Claude). I have also had long drawn out "arguments" when I have known it's wrong based on my experience and intuition, and it has steadfastly refused to take my point (last week)
I have learnt to ask it why it was doing something that has turned out to be incorrect, as a post-mortem, and it's all apologetic and subservient and "never going to do that again" (but still does as soon as the context window shifts [eg. run git commands, or, yesterday, kept telling me to use commands that were explicitly communicated to Claude as not being available, and completely wrong - I was shifting from one tech stack to another and Claude kept telling me the original commands, not the new ones])
I'm expecting Claude to be a better search engine - I have spent literal years (if not decades) knowing that asking the right question is what's required to get the right answer, and LLM's natural language processing is what's supposed to make that easier than using Google or grep, or even Stack Overflow - but the reality is that I still have to be on my toes, especially when I am drifting into territory I am unfamiliar with.
Pretty much everyone takes it at face value unless we know otherwise from prior experience. Even the most advanced models make embarrassing mistakes and fumble with simple tasks. Yet we are very willing to give them exceptional slack for it? I wish I knew why. Are people just that easily overcome by confident voices?
Back in high school, my AP calculus class did some experiments with our teacher's blessing. We'd send a kid out to walk around during class and see how long it took for them to get sent back. Anyway, it ends up that walking around purposely with a piece of paper or envelope, like you're on a mission to deliver it, was a very successful tactic.
The more concrete machine authority figure is also prevalent in scifi literature. Sometimes, I am not even certain if the author is doing this to examine this issue versus just leaning into it as either appealing to themselves or to the perceived audience.
Maybe because when it's right it actually expands my knowledge - there have been genuine instances where it's gone - something to the effect of - "Yo, there's this other idea for approaching the problem" which has turned out to be exactly what I was looking for?
Ironically, trying to argue with Claude about the limitations of LLMs and AI in general today is quite hard. It refuses to yield, likely due to Anthropic tweaking it aggressively
When one person is able to do too much too quickly, they can create more liability than they can accommodate if something fails.
It is essential that a human is responsible for the utilization of any AI output in the real world, but that is not enough. For our own sakes, we must find ways to minimize the tech-debt bankruptcy blast-radius of those who would utilize (knowingly or unknowingly) AI to create flawed systems upon which others rely.
An example: Jim vibe-codes an extremely popular micropayments app. He hires a few people and sees the company as the WhatsApp of money -- a few engineers and some agentic support staff. It pulls in a few million in VC money -- enough to draw in tens of millions of users. One day, a flaw in the infrastructure causes all of the users' unsalted banking information to be released.
Agentic AI allows that entire list of customers to be exploited rapidly, so the losses for society are in the tens of billions. Jim's company is immediately bankrupt, of course, but there are only a few million dollars to go around.
Today, most of Jim's incentives are to go ahead and build that app. The same is true for his few employees and a small VC contribution. There's not much capital at risk compared with the societal exposure.
How do we ensure that AI users are accountable not just for their actions, but for the size of the risk-exposure that they create?
“Sorry, the AI said that you are not approved for this cancer treatment, it’s not going to be covered.”
“Sorry, the AI said that you were at the scene when the crime took place.”
“Sorry, the AI has flagged your account for inappropriate content.”
“Sorry, the AI says that you are too risky to lend to.”
…
This, but web scale.
[Spoiler: ‘human’ is the name of their LLM agent]
I understand there is a push/pull with regards to how much we should let them do, but to not even look at the results before you make them somebody else’s problem? It’s just selfish. There’s no other word for it. You are simply taking the work you were supposed to do it and dumping it on somebody else. These are probably the same people who get upset (rightfully so!) when somebody doesn’t proofread their article/blog before publishing it online.
Everybody wants to use LLM’s to cut corners on their work but nobody wants to be downstream of it. That simply doesn’t work.
Brainstorm N ways to do X. Sort by probability.
Don't outsource all of your thinking.
If you have a competent user it can be quite powerful
When left to its own devices with the instructions "make an assembler for the architecture in ISA.md" -- well Claude picked Python as the implementation language. Tokens lifted through a bunch of regex. No expression parser! Oh dear. My first assembler was like that too, to be fair.
However, when I described the desired passes and their types:
collectDefines :: [SourceLine] -> Either AsmError ([SourceLine], Map Text Text)
runLitPool :: [SourceLine] -> Either AsmError ([SourceLine], [(Text, LitKey)])
evalExpr :: Text -> Map Text Text -> Either AsmError Int
Like - it can do the work for us.
It jives with post training and verifiable rewards.
The reason AI doesn't do well at 'architecture' is 1) are are bad at it and have given it a lot of mush and 2) we don't have good abstractions for it.
The result is - you stick to 'very strong conventions' and if you walk of that path you're risking a lot.
Toolchains are very deterministic, the AI can take it apart and re-assemble like Lego - and each level of the space is also deterministic. It's perfect for AI.
Maybe it's time for an architecture-oriented programming language?
But there's something existential there maybe?
NASA says, any time you make a program that has a new 'launch vehicle' (aka architecture) - the whole project is the 'launch vehicle'.
'Oh, you want use a new architecture? Welcome to the cesspit of hallucination!'
Basically, there's a lot more complexity than we might imagine 'hidden in the nothingness' of he unknown.
Pick a 'known off-the-shelf launch vehicle' first ... then you design the landing craft
Brainstorming and research before writing a design.
Writing a design or spec before writing the code.
Comprehensive unit tests.
Etc etc etc.
Like you, I get vastly better output from the tool when I create a detailed spec in markdown before I let it start coding. And bonus, the LLM is pretty good at helping with the spec too.
Even just saving me the time to deal with CI is worth it.
If this is true how can you confidently make this assertion.
You yourself are not in a position to evaluate it, you are just running it through a couple times hoping for a "oh wait, you're right to call me out on that, that is not correct at all".
"Here's my idea, go build it please"
"Can I ask you questions about it?"
"Hey, You're the engineer you figure it out. That's why I pay you"
Tale as old as time
As if code written by devs at major corporations is't mediocre at best.
Nokia's Symbian OS took days to build. Days. With a D. Not minutes, not hours but days.
One of our devs shipped code to prod with a memory leak thanks to including a library that had "do not use this library in production because it causes a memory leak" written everywhere as warning.
So I don't wanna hear about how poor AI code is when human code is shit too. Human laziness and stupidity can beat AI hallucinations.
Sure, maybe your DeepMind, OpenAI devs and your John Carmacks of the world can beat AI code 100% of the time, but most workers most companies get don't have John Carmack as candidates.
Everyone is aware that humans write poor code and treat the code as so. Not so with AI code. I’ve seen devs and managers cut corners in testing/reviewing code cause AI wrote it and they think it’s solid. Sure you could blame anyone cutting corners, and that would be technically correct, but the notion is so deeply embedded in many managers and higher ups that’s it’s hard to fight back. AI companies push this narrative and many individuals who do not routinely use it believe it. There is a manager at my company who loves to reference a video anthropic released last year claiming that Claude could build an app start to finish essentially unaided. He believes it’s the lack of user skill that’s the issue and not a false claim by a startup trying to make as much money as possible.
Good for them. I hope they believe this because one of two things will happen.
Either they win on the free market because they went all in on AI and beat their competition thanks to AI productivity increases.
Or, their AI code is shit and they collapse and go bankrupt, and get beaten by the competitors using human written code so then they win on the free market proving AI is useless.
So if AI is good or bad for productivity, the free market will ultimately decide.
My take is that AI is just an amplifier of existing skill. 1x devs using AI can use it to be 10x devs, 10x devs can become 100x devs, while -1x devs will be -10x devs and so on.
Irony is using Claude to write a beautifully structured, 2,000-word essay warning the industry about the dangers of letting Claude design things. It’s self-awareness by proxy.
"The accountability gap" Here’s the question nobody’s asking: when it goes wrong, who carries the bag? (..)
"What to do instead"
"The craft still matters"
> That’s not fair. And it’s not smart.
The amount of AI slop that makes it to HN is concerning. I don't know whether readers here don't care or don't notice it anymore. Or maybe they are only reading the title and then commenting? My #1 tell is an article that's suspiciously long without any real "story", that is, pictures of someone hacking at a laptop. It's always 20,000 words AI hate, ironically.
A good architect’s most important skill isn’t designing systems. It’s knowing which systems not to build. It’s pushing back on complexity. It’s asking “why?” five times until the actual requirement emerges from the aspirational nonsense. It’s telling the CTO that their conference-inspired idea is a terrible fit for the team they actually have.
AI agents are pathologically agreeable. Ask Claude if your idea is good and it’ll tell you it’s good. Ask it if a microservices architecture makes sense for your three-person team and it’ll explain why microservices are an excellent choice. Ask it if you should build a custom ML pipeline instead of using a managed service and it’ll enthusiastically lay out the design.Braindead.
Like any tool, it takes effort to master and configure. Before LLMs, I used cookiecutter templates to codify my best practices. Now I invest in custom skills and context management so the tool produces solutions that match my standards and team conventions.
I agree with the author that the craft still matters, and probably now more than ever. I'd add that mastering and configuring your agent is now part of the craft.
> It’s just incapable of the thing that makes a real architect valuable: saying “no.”
From my experience Claude is excellent at saying "no". It won't say "no" if the prompt doesn't call for it (it won't say "no" to your direct request to do something, usually). But it offers good critique and happily pushes back if you make it clear that that's a first class option.
So I was blunt, and said "I don't care about the burn-rate on some hypothetical chart that you produced at the start. I care about removing bugs and having a robust product, which this approach is satisfactorily doing. We will continue along this path, if the tests are not showing gain, then the tests are poorly designed".
At which point it got all apologetic, wrote new memories, and we didn't have a problem thereafter.
The issue was that I was attacking a huge bug-surface, and although each bug-fix was valid, correct, and helped move the dial, it didn't move the dial on the test-bed that Claude had created to measure its work against. There were too many inter-connected bugs for a single fix to really make a difference to these higher-level tests. I knew it was going to take a while to get through them, but apparently Claude didn't.
You try changing the size of a pointer from 2 bytes to 3 bytes on a compiler[1] for a 6502 while introducing automatically-tracked bank-switching on your memory-managed pointers, and see how many code-sites that impacts [grin].
[1]: https://atari-xt.com
An interesting experiment would be to try having the agent annotate the code with the relevant spec section while it's extracting the spec, then to have the agent update the spec with the new requirement - as an explicit change with something like "This section updated in V2 with...." - and have the agent update the codebase from that.
Some of these problems do just need breaking down a little further than you'd think to make the agent's life easier. This might be one of them.
It sounds like a boss. How soon will it be?
If you ask it with a prompt that leaves room for criticism it’ll definitely go for it when warranted.
Gemini is the most aggressive where it often picks on things if I leave out "the obvious" details, GPT somewhere inbetween, and Claude less so but still does it.
The article kind of lost me here. Agents are way more than that, today. And the author knows it, as later it says stuff like
> Claude will never do this. It’s trained to be helpful.
But the first phrase just tell me author just have a deep dislike for agents and it's looking for rationalizations for that feeling.
Part of the criticism is on point, sure. But if it "being trained to be helpful" is a problem, it's fixable. It can "be trained to be more critical".
Later:
> But it wasn’t designed for your team. (..) It was designed for the median of everything Claude has seen. A generic best practice for a generic problem at a generic company. Which is to say, it was designed for nobody.
That's non-sense. Anybody who understand algorithms know that, sure, on a first instance you have a "good algorithm" that has a good performance on average, or in worst-case. But then, you can design algorithms that are adaptive to the input. Same applies here.
Not really though. They just iterate more and more.
I try to not re-iterate too much, but maybe thats due to me not wanting to work and working for a startup so time and motivation are hard to find.
For what it's worth, Opus tells me that I'm wrong and not to do things all of the time. When I reflect on why that is, it's because of the way that I prompt it. You could say that I am subconsciously avoiding setting both me and the LLM to fail in the way the author projects as inevitable.
Specifically, I don't come to it with prompts that resolve cleanly with "tell me how clever I am" replies. I always present myself as a domain expert - because I am a domain expert - and I make it clear when I am open to getting input on the pros and cons of different paths.
With a conclusion that will be unsurprising to any successful LLM daily drivers, this strategy has been remarkably effective.
Me: I have two bits and need to mill some 5mm aluminum.
A Makera Spiral 'O' - 1/8" shank * 12mm or a carbide 6.35 * 22 * 50
I believe that they are both carbide single flute bits, but the 2nd one seems like it would make short work of 6061.
Claude: The Makera 1/8" single-flute 12 mm is the sensible choice.
The 6.35 × 22 × 50 mm bit may look like it would make short work of 6061, but on a Carvera it is probably the more dangerous choice. It is a much larger cutter, with much more engagement, and it asks more from the spindle, frame rigidity, workholding, and chip evacuation. In a small dry machine, “bigger” often becomes “more chatter and more heat,” not “faster.”
----
TL;DR: Claude doesn't seem to have any issue telling me when I'm wrong.
It will tell me a suggested abstraction is probably overkill and just to make a component own the new thing I’m discussing.
What I’m missing from the loop is it later saying without directly prompting, “hey it’s time to revisit that abstraction idea.”
(I still prompt some questions and reviews with "our intern suggested..." to allow models to judge the quality of the content apart from the messenger)
Tangentially, the usage of Architect keyword sounds out of place here, I don't like saying it but from what I seen the industry has destroyed the role of architects gradually over the time. There are specialists however you do not have generalists who are good at different parts of the system at scale anymore.
Just tried this. Claude Opus replied “probably not” and recommended a well structured monolith.
There is also a mountain of bullshit eg "[architectural|design] [anti]patterns" that are written mostly (I would argue) to sell something (consulting, hardware, etc). This is typically at odds with a good solution.
There is a relative lack of actual documented architectures that work. Not only do you need the details but also the usage of these systems so as to judge what "good" is.
We will probably just go the HTML route with architecture: take a really bad base and just keep throwing compute, memory, and network I/O at the problem until it works.
Note to self: invest in energy ETFs.
Mostly these things are the secret sauce (or at least primary ingredients) underlying all the successful products you've heard of. Over time the secrets come out in the form of papers, blog posts, and open source software. But often the cutting edge isn't public because it's in this or that company's private, proprietary codebase. As people move between companies the knowledge diffuses, but if you're relying on a model that was trained on last year's public code you're at least a few more years than that behind. And it's even worse than that, because correct patterns--ones that actually work well--are underrepresented in the dataset.
Garbage in, garbage out. I don't understand what people are hoping for with this whole "agentic" thing... Autocompleting the function I'm currently working on is potentially useful, provided it produces acceptable code more than.. idk.. 95% of the time. "Agentically" building larger system components? Nah.
Well, can you prompt it to think about the problem?
> A good architect’s most important skill isn’t designing systems. It’s knowing which systems not to build. It’s pushing back on complexity. It’s asking “why?” five times until the actual requirement emerges from the aspirational nonsense. It’s telling the CTO that their conference-inspired idea is a terrible fit for the team they actually have.
Except for that last one, that all sounds very solvable. Of course, the last one is the most important one. But most humans will struggle there too.
However the good part, what I had planned for 5 years, now looks like doable in 6 months. Looking forward to real use by the end of this year.
Yes, that's assuming you take time to clean up now and then. If you don't, that's on you.
I don’t doubt the problems in this article exist and I’ve seen them, in my experience the vast majority of people are still shipping the same quality or better than before they has Claude. Personally, I feel like I’m probably developing at about 1.5x the speed of not using AI tooling. It’s not a silver bullet, but it can be a great assistant.
Every decision that matters? Some, yes. Is the author only noticing the decisions that go wrong?
So... manually learn architecture and security and then vibe code away?
Does so many people in HN just upvote by title?
It doesn't disappear when you make 1 person do the work of 3. It simply is aggregated
Suppose you had a pod of a PM, designer, and analyst. Leadership lays off the designer and analyst and now the PM can move faster with AI. Hooray!
Well...when the complaints about how it looks on xyz device roll in, who is implementing that? Or you launch the product with much fan fare, adoption is terrible - you double check the numbers and oops, the sizing you had from Claude was actually 10x off.
Who is holding the bag? You are! Not Claude
I'm convinced this is one reason we are seeing slower than expected adoption of AI broadly in tech companies, because it's hard to trust - we know Claude can make mistakes but how do you know what's right vs not? Most people don't want to sense check so they just keep doing the work the way they know best.
I think this could be one thing that pops the AI bubble - execs try to force this, people go along, and results are not any better for this reason. Sure you save some salaries and ship more quickly, but you don't build the right thing and you are fixing more things after launch. Which one is actually better?
The thing that I find Claude incredibly good at when I'm designing architecture is working more like a research assistant on briefing decisions. It has the ability to read the entire code base and draw some conclusions. It can pull from lots of best practices and the millions of blog posts about this or that pretty effortlessly, which would take me a lot more time.
And then if asked, it can do a really good job of laying out the landscape around decisions and walking through the trade-offs. Like the author of this post, I found that if you let it, it will certainly be happy to just come up with some architecture and run with it, often in ways that will paint you quite rapidly into a corner.
But if you ask it to present you with all the trade-offs and let you make the judgment calls, it's great for that too.
That's certainly how I use it. And I think, just like anything else, working with AI is a skill, and similar to working with libraries, SaaS providers, service providers, frameworks, or anything else that's a "helper." You learn how something that could work but will fail silently is a problem, or you learn how depending on a fly-by-night SaaS company for a key framework is different than depending on a well-populated open source project, etc.
In the same way, you learn that relying on Claude's judgment is a bad idea, while relying on Claude's ability to summarize, brief, and research can be incredibly efficient.
We can describe this without talking about technology - so pre-AI.
Imagine the owner of a construction company firing all the architects. After all, he's been the owner for 15 years. He has led the construction of dozens of projects. He's also rich, and being rich seems to be an ego-multiplier.
Why should he waste money on architects? Or more importantly, why should he allow them to constantly annoy him with pushbacks: "This could be a problem if the sustained wind is greater than ... ".
Those engineers obviously don't know the real world. Their elitist education has made them afraid to make bold decisions. Regulations are anti-progress!
Thankfully, that owner now has AI tools. He doesn't need those not-always-yes-people. He now has a perpetual yes-bot.
So where are we now? We're in the same place we always have been. People need to have the humility to recognize that despite their authority, influence, or wealth, they still need other people. And especially, they need other people to challenge their orders or their requests.
But I don't really see this situation self-correcting. There's now so much money concentrated amongst a few who will spray it over exactly the kind of people who do not want to listen to others that most activity in the future will be for naught. Yes, some unicorns will be fabricated, and some people will make a lot of money; but real value will not be created often.
Therefore, I implore the actual thoughtful creators: Do build things, but do not sell out. Look to the past. Create companies where every employee was valued, and every employee had some voice. Yes, use AI. But test and measure where it really helps. And be skeptical, just as you would if someone came to your door promising a black box that would double your profits.
For any nontrivial task I spend 2-8 hours in specification (I spent 3-4 hours on a stateless rust CLI tool design this weekend) and detailed task breakdown in implementation planning.
I use TDD to start with red tests that turn green when acceptance criteria are met.
I write agents to use to check work and they are my enforcers of constraints, as well as fresh eyes. I use these agents for spec review, plan review and code review.
I am actually pretty proud of the projects I create with generative AI. I just apply a lot of discipline so I don’t end up with slop.
So it's the person using the AI that's the problem, not the technology itself?
I ask for multi-turn evaluations and often times parallel sub-agents to get consensus about something, there is plenty of back and forth. Sometimes I have to tell the AI to shush up and that we're doing things the simpler not more correct way cause we need to ship sooner, but generally with enough exploration most ideas are pretty good. As long as you literally don't rubber stamp everything, Opus does an okay job (I also tried out DeepSeek, that one was a bit worse at planning but passable).
Then again, I doubt the CTO in question ever is like: "Okay, after reviewing these other 3 projects that I put in your workspace for comparison against prior work and all of those other documents that provide context, and after writing this detailed plan, would you like to ask me 20-40 additional clarifying questions before we lock in on this design? Anything that is not completely clear or ambiguous."
I have noticed that better results come from throwing more compute at the problem, though. Even in regards to writing code, it will produce something that is sometimes arguably slop, but when there are 3 parallel sub-agents reviewing any changes before commit, often it will surface multiple rounds of fixes in the review loop until none of them find any serious/critical issues.
> Real architecture is full of trade-offs that only make sense in context. You pick Postgres over DynamoDB because your team knows Postgres and you’d rather ship in two weeks than spend a month learning a new data model. You skip the service mesh because you’ve got four services, not forty. You use a monolith because the problem is simple and microservices would be career-driven development.
I also think that all of this should be encapsulated in ADRs or any kind of docs. Then you can point whoever joins the team, or your LLM tools, at the folder and let them get brought up to speed, instead of having to track down whoever wrote a particular piece of the system for questions, or have to do digital archaeology in old Jira issues.
I thought this happened alot. I started using chatgpt to critique my new art hobby and also help me learn unreal engine.
It's basically tearing into me on the art. It's almost ruthless, especially with the verbosity it's like I get it.
Using it for unreal engine, it pushes back on alot of my begginer ideas and how to write code that uses the engine. It corrects me alot. It's called things I wrote becasue I was lazy sloppy or quick hacks that work for now.
In my workflows Claude does pushbacks all the time and justifies why. There is back and forth just like a colleague. It’s not perfect but the results are usually good
This.
If you ask it to be fair and non-biased and provide pros and cons and give possible alternatives - it will. The catch - you might understand the explanation if you don't know the domain good enough.
Overall - a very, VERY good article, thank you!
I then logged in from completely different account, described the problem and asked to design architecture of backend with the same functionality and performance. Suddenly I got standard distributed enterprise monsterware running on amazon. Yes - it could do the task for at least 100-time price for comparable performance and way more complex to manage at even more markup
I then have merged both conversations and started grilling Claude why is it doing such a disservice to a customer who is looking to optimize ROI.
Claude's answer was basically - It runs on large corporate's development methodologies / propaganda that outweighs every rational choice just because of sheer volume
So yes, be careful what you wish AI to do. It can and will set you up.
It’s been quite good for my productivity and the best part for me is that I learn what I’m writing while I’m writing. I can just write things I already understand a lot faster than before. When I work with agentic, I find that I still have to deeply learn the system, but I’ll have to learn it when it falls over instead of at review time.