My workflow is something very similar. I'd say one difference now is PRs actually take longer to get merged, but it's mainly because we ignore them and move onto something else while waiting for CI and reviews. It's not uncommon for a team member to have multiple PRs open for completely different features.
Context switching is less painful when you have a plan doc and chat history where you can ask why yesterday afternoon you (the human) decided to do this thing that way. Also for debugging it's very useful to be able to jump back in if any issues come up on QA/prod later. And I've actually had a few shower thoughts like that, which have allowed the implementations of some features to end up being much better than how I first envisioned it.
Odd how you add the time for the requirement analysis but none for the coding.
Then you tell us you leave 83% of the analysis —and the coding— to a code chatbot.
Are you actually more productive or are you going to find out down the line the chatbot missed some requirements and made APIs up to fill up a downstream document and now you better support them by yesterday?
In ye olden days, people doing this would scream at the junior developers. Are you going to scream at your screen?
To be honest, I didn't think too hard about it. I just fired and submitted with the time estimates in there kind of randomly.
You are clearly a naysayer. I get it. I was one too for a long time. Then I found a workflow and a model that was clearly delivering results and that's what I use now.
It's only a matter of time before it happens to everyone, even you. Once you have the aha moment where it works for you, you'll stop asking everyone whether they really know if it's better.
The LLM-based workflow above produces good code at a speed at least as fast as my previous workflow and typically many, many, many times faster with the code produced often using designs I would have never thought of before being able to bounce ideas off an LLM first. The biggest difference, besides the time obviously, is that the energy I need to spend is in very different places between the two.
Before it was thinking about what I needed to do and writing the code.
Now it's thinking about what I need to do and reviewing the code.
Well, I'm not considering using any code generation outside of helper scripts because in my case coding is a negligible part of my work. If I didn't have the LLM, I would find and modify the tool it is lifting code from using pre-LLM Google.
I know asking one of these LLMs to produce a document from my notes, resulted in me having to review this professional and plausible-looking yet subtly wrong document for more hours than it would have taken me to produce the document from scratch.
Of course not. But I used to know a group of guys who were born fabulously wealthy. None of them were happy. For them to get a job it would be essentially working for free relative to the wealth they have.
I'm sure there are people out there who would find meaning in creating art of some type, or turning their fortune into an even bigger fortune, but I suspect those people are rare.
The people I know who do not have to work to ensure healthcare for their kids seem happier than the ones who do have to work. Being able to go on vacations for extended durations or at convenient times is also heavily utilized.
I’d argue it’s more an attribute of being a driven, difficult to satisfy, competitive, human.
Which correlates strongly with ‘success’ in any system where there is a clear metric for success, which is certainly true for our current economic system eh? If there was a system they wanted to compete in where the metric was ‘happiness’ measured by some concrete metric, I bet those same people would be as aggressively ‘happy’ with however it was measured too - and just as actually miserable.
That those people are rarely (if ever) happy is a side effect of those attributes, and a core part of what makes them the way they are.
After all, if they were able to be happy with anything less…. They’d have stopped already? And hence have less/a lower ‘score’ on that particular metric? And probably actually be happier.
Notably, I know plenty of people who are very happy with nothing - dirt poor - and plenty of people who are also miserable with nothing too.
The difference is, it’s a lot less competitive being dirt poor eh?
Either side of an analogy can have factors at different scales. But it can still be a valid analogy.
If you are saying that because slavery was much worse, then modern slaves should just suck it up and work harder. Then that isn't really helping is it?
This is kind of the argument "others have had it worse, so lets not try to make anything better for people today".
Are you seriously equating the modern office and work, where, you know, you can go home after, to life as a slave on a plantation? Sure, analogies can have factors at different scales but the scales come into the equation when the factor is the axis we are analyzing.
Is your issue that life requires action to maintain it? Do you believe no work is required at all in life? The idea that work is like slavery is deep when you're 14 and then not so much.
No one had said our modern lives couldn't be better but you don't have to liken our existence to slavery to get to "things could be better".
Okay if not American Slavery what's your benchmark? Having to do things you don't want? I'm being serious. You use extreme language and hyperbole so it's hard to take you seriously. Do you think your situation is akin to like, someone being held hostage in a call center and forced to scam people? Where is the line, in your mind?
Because it is a hard line to draw, doesn't mean I'm not being serious.
You are objecting to using the word 'slave' as a descriptor, except in extreme cases.
But the term slave is often used in culture for a lot of things.
Being a 'slave to your addictions', 'a slave to your desires', 'an office slave', 'wage slave'. etc.... I'll spare you a list of hundreds of examples.
I think since you are the one objecting, then you draw the line.
I tend to think it does hinge on 'agency'. If you are trapped. But, sure, being trapped in an office today, is not as painful as being trapped as a slave in the US south. Does that mean the office worker should just shut up and deal with it, it is comfortable enough?
I do think agency is the fulcrum and concede I was being too pedantic. I do think even from an agency perspective it is possible to "drop out" to some extent but not completely, but that's why I asked about the work aspect. Even if you are not working a 9-5, life does require work. That some choose to toil the fields for their food or sit in a cubicle, you must work all the same. So are we slaves to life?
Maybe the problem is if you are working for someone else.
If you are toiling on your farm to survive. Or even hunting/gathering for food. You do need to work to live. So a slave to life? All life is a burden? Even Buddhist have 'all life is suffering'.
But toiling in an office, is usually for someone else's benefit. You are only getting a fraction of your work back in pay. So if you are 'trapped', unable to change, and working for someone else's benefit, then a 'slave'? (wish I had some Marx quote to fit here).
It is bit of slippery slope, since i'm not trying to include every person that just complains about working because they would rather play video games.
And yet, in a market system, the 'rat race', we all do have a sense that we are 'slaves to the system'.
The tools of slavery have evolved but the overall end goal has not. The almost cliché slavery depiction of the chain and whip had evolved into the coolie system, the offshoring system and the kafeel system. The office is simply a part of that family of exploitation methods. There is a difference between serving the collective good and being a slave.
Many of us want to work on something greater than ourselves, to contribute to society not out of selfishness or lifestyle, but to genuinely help society function and make people happy. Many of us aspire to make a small dent in the universe with something great, something that can stand the test of time, building a thing in defiance of our own mortality in the hopes that our ancestors remember us, learn from us and run with the torch of civilization, to improve the human project to a level of greatness that we may ourselves never witness. In a way, to create is one of the highest forms of self expression as a human.
This is entirely different from reality, where retirements are wiped out by financial sorcerers, after decades of fulfilling your end of the social contract, trading in your productive years to a company that _does not care about you OR your community_, where run away inflation, debt and taxation are used to funnel capital to other competing nations or a unwitting fifth column whether that is transmigrasi in Indonesia, the influx of Indians in Texas or the mass refugee stream to Europe caused by US-Israeli inflicted wars, which has already surpassed in numbers the transatlantic slave trade, the endless wars that balance domestic unrest with a common enemy to rally around the flag, and the accompanied transfer of wealth across nations as these warmongers decide which country gets axed to serve the greater powers. There is no saving for retirement, there is no freedom, there is only bondage, death and taxes.
Meanwhile, the collective fruit of western society is plundered through the illegal pirating of the intellectual output of millions of creatives who poured everything they have in it, and it is plundered by the very same class of people that sued common folk for pirating software, music, movies and books. Aaron Swartz would roll over in his grave to see how the government supports companies like Google, OpenAI and Anthropic who rely on plagiarizing IP at scale.
The collective fruit of an entire civilization’s labor is plundered before your very eyes right before they launch it into a cataclysmic war that wipes away the very people who dedicated their lives to the sciences and humanities in order to further the human project. To deal such a low blow is an atrocity that is worse in its impact than the plantation system, it is reminiscent of the bronze age collapse that leveled ancient Egypt.
No good deed goes unpunished, as Ozymandius found out the hard way.
And yet in the 200 years since human civilization has improved by every imaginable metric, in most cases by orders of magnitude. The difference between 2026 and 1826 is nearly incomprehensible. I suspect most people scarcely imagine how horrific the average life was in 1826, relatively speaking. And between then and now were the industrial revolution, multiple world wars, and generally some of the most terrible events, crooked politicians, and life changing technological forces. And here we are, mostly fine in most places.
I get there are many things happening today that are frustrating or moving some element of human life in negative or ambiguous directions, but we really have to keep perspective on these things.
Nearly every problem today is a problem with a solution.
The feelings of panic we have that things are going wrong are useful signals to help guide and motivate us to implement those solutions, but we really must avoid letting the doomerism dominate. Just because we hear constant negative news doesn't mean things are lost. Doesn't even mean things are bad.
It just means we have been hearing a lot of negative news.
This is what it looks like for progress to not be monotonically increasing.
In the general case it's usually not possible to accurately review an individual physician's performance. The software developers here on HN like to think in simplistic binary terms but in the real world of clinical care there is usually no reliable source of truth to evaluate against. Occasionally we see egregious cases of malpractice or failure to follow established clinical practice guidelines but below that there's a huge gray area.
If you look at online reviews, doctors are mostly rated based on being "nice" but that has little bearing on patient outcomes.
A friend of mine had such a bad experience with _multiple_ American doctors missing a major issue that nearly ended up killing her that she decided that, were she to have kids, she would go back to Russia rather than be pregnant in the American medical system.
Now, I don't agree that this is a good decision, but the point is, human doctors also often miss major problems.
Amazing how you can just deflect any criticism of LLMs here by going “but humans suck too!” And the misanthropic HN userbase eats it up every time.
We live during the healthiest period in human history due to the fact that doctors are highly reliable and well-trained. You simply would not be able to replace a real doctor with an LLM and get desirable results.
> Amazing how you can just deflect any criticism of LLMs here by going “but humans suck too!” And the misanthropic HN userbase eats it up every time.
I think it's rather people trying to keep grounded and suggest that it's not just the hallucination machine that's bad, but also that many doctors in real life also suck - in part because of the domain being complex, but also due to a plethora of human reasons, such as not listening to your patients properly or disregarding their experiences and being dismissive (seems to happen to women more for some reason), or sometimes just being overworked.
> You simply would not be able to replace a real doctor with an LLM and get desirable results.
I don't think people should be replaced with LLMs, but we should benchmark the relative performance of various approaches:
A) the performance of doctors alone, no LLMs
B) the performance of LLMs alone, no human in the loop
C) the performance of doctors, using LLMs
Problem is that historical cases where humans resolved the issue and not the ones where the patient died (or suffered in general as a consequence of the wrong calls being made) would be pre-selecting for the stuff that humans might be good at, and sometimes wouldn't even properly be known due to some of those being straight up malpractice on the behalf of humans, whereas benchmarking just LLMs against stuff like that wouldn't give enough visibility in the failings of humans either.
Ideally you'd assess the weaknesses and utility of both at a meaningfully large scale, in search of blind spots and systemic issues, the problem being that benchmarking that in a vacuum without involving real cases might prove to be difficult and doing that on real cases would be unethical and a non-starter. And you'd also get issues with finding the truly shitty doctors to include in the sample set, sometimes even ones with good intentions but really overworked (other times because their results would suggest they shouldn't be practicing healthcare), otherwise you're skewing towards only the competent ones which is a misrepresentation of reality.
The fact that someone would say stuff like "Doctors are more like machines." implies failure before we even get to basic medical competency. People willingly misdirect themselves and risk getting horrible advice because humans will not give better advice and the sycophantic machine is just nicer.
> I think it's rather people trying to keep grounded and suggest that it's not just the hallucination machine that's bad, but also that many doctors in real life also suck
No, you see this line or argumentation on every post critical of LLM's deficiencies. "Humans also produce bad code", "Humans also make mistakes" etc etc.
> No, you see this line or argumentation on every post critical of LLM's deficiencies. "Humans also produce bad code", "Humans also make mistakes" etc etc.
So your reading of this is that it's a deflection of the shortcomings?
My reading of it is that both humans and LLMs suck at all sorts of tasks, often in slightly different ways.
One being bad at something doesn't immediately make the other good if it also sucks - it might, however, suggest that there are issues with the task itself (e.g. in regards to code: no proper tests and harnesses of various scripts that push whoever is writing new code in the direction of being correct and successful).
Even in medicine, often the difference between drug A and drug B is the difference between the two in statistical terms. If drugs were held to the standard "works 100% of the time", no drug would ever be cleared for use. Feelings about AI and this administration are influencing this conversation far too much.
It's like people want to remove the physician or current care from the discussion. It's weird because care is already too expensive and too error prone for the cost.
Medical errors are one of the leading causes of death. It's a real catch-22. If you're under medical care for something serious, there's a real chance that someone will make a mistake that kills you.
You also don't sue for malpractice unless something goes catastrophically wrong. I've had doctors make ludicrously bad diagnoses, and while it sucked until I found a competent doctor and got proper treatment, it wasn't something I was going to go to court over.
We do in fact prosecute drug dealers. In fact, if anything China's opium problems of the 19th century were ended by communist cadres mass executing drug dealers (and some users) in the 20th century.
Many countries have successfully cut down sugary drink consumption through regulation.
Where to draw the line is a matter of policymaking decisions and its not black and white. Its a very gray area that needs to be tuned carefully by society.
- Think about requirement
- Spend 0-360 minutes looking through the code
- Start writing code
- Realize I didn't think about it quite enough and fix the design
- Finish writing code
- Write unit tests
- Submit MR
- Fix MR feedback
Until recently no LLM was able to properly disrupt that, however the release of Opus 4.5 changed that.
Now my workflow is:
- Throw as much context into Opus as possible about what I want in plan mode
- Spend 0-60 minutes refining the plan
- Have Opus do the implementation
- Review all the code and nitpick small things
- Submit MR
- Implement MR feedback
reply