I'll add "craftsmanship". It isn't just delivering "A" finished product, you want to deliver a "good", if not "the best", finished product.
I guess if you're in an iterative MVP mindset then this matters less, but that model has always made me a little queasy. I like testing and verifying the crap out of my stuff so that when I hand it off I know it's the best effort I could possibly give.
Relying on AI code denies me the deep knowledge I need to feel that level of pride and confidence. And if I'm going to take the time to read, test and verify the AI code to that level, then I might as well write most of it unless it's really repetitive.
I don't think AI coding means you stop being a craftsman. It is just a different tool. Manual coding is a hand tool, AI coding is a power tool. You still retain all of the knowledge and as much control over the codebase as you want, same with any tool.
It's a different conversation when we talk about people learning to code now though. I'd probably not recommend going for the power tool until you have a solid understanding of the manual tools.
It can be a power tool if used in a limited capacity, but I'd describe vibe-coding as sending a junior construction worker out to finish a piece of framing on his own.
Will he remember to use pressure treated lumber? Will he use the right nails? Will he space them correctly? Will the gaps be acceptable? Did he snort some bath salts and build a sandcastle in a corner for some reason?
All unknowns and you have to over-specify and play inspector. Maybe that's still faster than doing it yourself for some tasks, but I doubt most vibe-coders are doing that. And I guess it doesn't matter for toy programs that aren't meant for production, but I'm not wired to enjoy it. My challenge is restraining myself from overengineering my work and wasting time on micro-optimizations.
That's a really good point. And I agree that kind of confidence in craftsmanship is something that's missing from agentic coding today... it does make slop if you're not careful with it. Even though I've learned how to guide agents, I still have some uneasiness about missing something sloppy they have done.
But then it makes me ask if the agents will get so good that craftsmanship is a given? Then that concern goes away. When I use Go I don't worry too much about craftsmanship of the language because it was written by a lot of smart people and has proven itself to be good in production for thousands of orgs. Is there a point at which agents prove themselves capable enough that we start trusting in their craftsmanship? There's a long way to go, but I don't think that's impossible.
Maybe the internet has made me too cynical, and I'm glad people seem to be having a good time, but at time of posting I can't help but notice that almost every comment here is suspiciously vague as to what, exactly, is being coded. Still better than the breathless announcements of the death of software engineering, but quite similar in tone.
The other week I used Copilot to write a program that scans all our Amazon accounts and regions, collects services and versions, and finds the ones going EOL within a year. The data on EOL dates is scraped from several sources and kept in JSON. There's about 16 different AWS API calls used. It generates reports in markdown, json, and csv, so humans can read the markdown (flags major things, explains stuff), and the csv can be used to triage, prioritize, track work over time. The result is deduplicated, sorted, consolidated (similar entries), and classified. I can automatically send reports to teams based on a regex of names or tags. This is more data than I get from AWS Health Dashboard, and can put it into any format I want, across any number of accounts/regions.
Afaik there are no open source projects that do this. AWS has a behemoth of a distributed system you can deploy in order to do something similar. But I made a Python script that does it in an afternoon with a couple of prompts.
I am currently using a Claude skill that I have been building out over the last few days that runs through my Amazon PPC campaigns and does a full audit. Suggestions of bid adjustments, new search terms and products to advertise against and adjustment to campaign structures. It goes through all of the analytics Amazon provides, which are surprisingly extensive, to find every search term where my product shows up, gets added to cart and purchased.
It's the kind of thing that would be hours of tedious work, then even more time to actually make all the changes to the account. Instead I just say "yeah do all of that" and it is done. Magic stuff. Thousands of lines of Python to hit the Amazon APIs that I've never even looked at.
It's thousands of lines of variation on my own hand-tooling, run through tests I designed, automated by the sort of onboarding docs I should have been writing years ago.
Do you trust the assembly your compiler puts out? The machine code your assembler puts out? The virtual machine it runs on? Thousands of lines of code you've never looked at...
We agree then that you can verify, test, and trust the deterministic code an LLM produces without ever looking at it.
> That's one reason we test
That's one way we can trust and verify code produced by an LLM. You can't stop doing all the other things that aren't coding.
I get there's a difference. Shitty code can be produced by LLMs or humans. LLMs really can pump out the shitty code. I just think the argument that you cant trust code you haven't viewed is not a good argument. I very much trust a lot of code I've never seen, and yes I've been bitten by it too.
Not trying to be an ass, more trying to figure out how im going to deal for the next decade before retirement age. Uts going to be a lot of testing and verification I guess
- A slimmed-down phpBB 2 "remake" in Bun.js/TypeScript
- An experimental SQLite extension for defining incremental materialized views
...And many more that are either too tiny, too idiosyncratic, or too day-job to name here. Some of these are one-off utilities, some are toys I'll never touch again, some are part of much bigger projects that I've been struggling to get any work done on, and so on.
I don't blame you for your cynicism, and I'm not blind to all of the criticism of LLMs and LLM code. I've had many times where I feel upset, skeptical, discouraged, and alienated because of these new developments. But also... it's a lot of fun and I can't stop coming up with ideas.
Also scientists generally suck at messaging and persuasion. They think if they just dial up the stakes and consequences a little more, it'll be compelling! Maybe if we make one more documentary with bad CGI disaster movie scenes, that'll do it! Same with the stupid "Doomsday clock" that is somehow always "the closest we've ever been to nuclear war!" whenever it gets trotted out. You'd think people who know what stochastic noise is would realize when they're producing it.
They would have made a lot more headway talking about clean air, clean water, jobs, and a bright prosperous future where we manufacture wind turbines, batteries and solar panels in deep red Missouri. A minority tried that, but most stuck with the catastrophizing for decades and now that they've ruined their social credit no one will listen to the message they should have opened with.
You need people emotionally invested, and it's a lot easier to get them invested in their lives than in the abstract consequences of computer models that are at least 100 years out if they're even accurate. And most people are not independent enough to direct their own lives. If they make the right decisions on abstract concepts, it was more because the incentives/disincentives in their environment were set up correctly than they actually understood the decision they were making. Message accordingly.
Every approach you've suggested above, and others besides, has been tried by scientists, NGOs and government agencies for the last few decades, and largely failed.
The IPCC has consistently DOWNPLAYED the negative consequences of climate change, and reality keeps outpacing their worst case predictions year after year.
Every attempt to message the reality and consequences of climate change, and the possible avenues for blunting it, has been tried. From the sugarcoating "everything will be rosy and great and abundant, look at all the benefits of green industry" to the milquetoast watered-down try-to-please-everyone messaging of the major political parties, to the desperate attempts to communicate the brutal reality of what we're facing (and still failing to match the reality that is consistently worse).
None of it works.
1) People are selfish, myopic, and stupid. They think about their short term personal needs and wants above all else. Large scale coordination on this issue is virtually impossible, see the Prisoner's Dilemma. Human psychology is simply not fit for this task.
The satisficing nature of evolution means we are the dumbest possible animal that could otherwise achieve the technological civilization that we have, and this is another example where it really shows.
2) The wealthiest and most powerful people and corporations on Earth have spent decades pushing propaganda attempting to sow doubt about climate change, because genuine action on it is directly against their interests.
Those poor multi-trillion dollar industries underpinning all modern society and power structures are the altruistic, honest bastions of truth, it's those evil corrupt post docs on minimum wage that are the truly corrupt and greedy ones, twisting the truth for their own financial gain and machiavellian ends!
And they've been far more effective than the cigarette companies of the early 20th century could have ever dreamed.
> The IPCC has consistently DOWNPLAYED the negative consequences of climate change, and reality keeps outpacing their worst case predictions year after year.
Except downplaying consequences downplays the upside, i.e. opportunity.
The dire warnings should be dire, but paired with a call to opportunity opportunity opportunity. Instead of focusing on enemies or little inconvenient things we could all do, if only we could all be uniformly focused and high minded enough as uncoordinated individuals.
That fact that virtually every way we can reduce climate damage involves new capabilities and resources with additional economic and health benefits (not to mention political disentanglements) makes positive self-interested calls to profitable action much more sensible.
And political leaders shouldn't be afraid to work with the CFO's of fossil fuel companies to create incentives they want. It might be costly, but CFO's get flexible when there is a clear path to making more money. Any costs of smoothing that path (let's be clear, in a way that would be pure corruption if the size of the problem didn't make that a value creator) are nothing compared to the costs of climate change.
China gets it. (Not uniformly of course, but more, and its paying off for them.)
To be fair, he sounds a little more intense than your average player:
"A psychologist concluded that Friedmann suffered from dysthymia, today known as persistent depressive disorder, and schizoid personality disorder, writing that he showed “indifference to social relationships and a restricted range of emotional experience and expression.” He also had a tendency to “blur fantasy with reality.”
Friedmann was convicted of armed robbery and attempted murder"
"If you aim well enough" is doing a ton of work there. Precise real-time optical tracking of a satellite from a moving platform is an extremely difficult problem. Even if the satellite itself is geostationary, it would also have to rotate to keep the "cylinder" pointed in the right direction to maintain signal.
I suppose you could make a "cylinder" or "cone" broad enough that, if the threat was static, could blot-out attempted jamming from only certain regions while staying open facing toward friendly zones.
No, but the airplane it would be talking to does. Hard enough when your transceiver is wide open, if you narrow your FOV to a thin cone in order to block jamming signals, the GEO now has to physically track the airplane somehow.
Either the whole satellite rotates or the transciever is on a mount that can rotate
Unless you plan on having 1 satellite per airplane, something tells me it's harder to constrain the FOV than you might suggest. There's also the small problem of the energy, complexity, & weight of having motorized parts on the satellite (or fine-grained attitude control for the satellite itself to track the craft).
Agreed, my point is it's a lot harder than tiagod made it sound.
It also doesn't account for some kind of mobile jammer making it inside the cone, particularly if it's staring at an adversarial nation where secure comms would be needed the most, but the adversary would have freedom of movement.
Welcome to the return of history. This is hardly the first time or industry where the US government has forced compliance that wasn't necessarily in the public interest.
And the corporations won't fight this. They're in it for the money and they're willing to bring actual gold bars to White House to ensure it keeps rolling in. They know what they're doing is corrosive and debasing, the more conscientious of them probably want to vomit on the inside. But they mostly suck it up and do it anyway, for their investors will discipline them if they don't.
Either people run candidates and vote for the ones that campaign on stopping this, or it happens.
Worse: they'll be sacked and replaced with someone who will.
Like Trump's FCC chair was saying he'll revoke the license of stations that make republicans look bad. Those stations will then be replaced with more copies of Newsmax. CBS either toes the line or it gets shut down and replaced by a station that will.
The idea that somehow the current actions are 'real' history and what people were doing before is fake just feeds the claim of inevitabiility, a basic psyops maneuver - you can't win; our victory is inevitable.
People have made history for centuries of Enlightenment - the whole idea is that we can control our fates as individuals through reason and compassion (humanism), and we have done it. We have transformed the world. The only problem is people giving up - despite the incredible success of this idea over centuries - and accepting that they can't control their fate. Certainly MAGA-ish conservatives believe they can make history.
"The End of History and the Last Man" was a book written in 1992 about the end of the Cold War and how previous historical patterns no longer applied, and Western liberal democracy would sweep the world and usher in a world of peace.
The "return of history" is snarkily pointing out how historical trends have been reasserting themselves, and Fukuyama (the author) was, at best, overly optimistic
Also hiring. It's easier to find people with JIRA experience than people in your vibe-coded ticket manager, even if it is technically superior for your application.
If there is any commonality between the 3D printing craze and vibe-coding, they're both renditions of "just because you can, doesn't mean you should".
> Every frontier tech company is convinced that the tech they are working towards is as humanity-useful as a cure for cancer, and yet as dangerous as nuclear weapons.
Maybe some of the more naive engineers think that. At this point any big tech businesses or SV startup saying they're in it to usher in some piece of the Star Trek utopia deserves to be smacked in the face for insulting the rest of us like that. The argument is always "well the economic incentive structure forces us to do this bad thing, and if we don't we're screwed!" Oh, so ideals so shallow you aren't willing to risk a tiny fraction of your billions to meet them. Cool.
Every AI company/product in particular is the smarmiest version of this. "We told all the blue collar workers to go white collar for decades, and now we're coming for all the white collar jobs! Not ours though, ours will be fine, just yours. That's progress, what are you going to do? You'll have to renegotiate the entire civilizational social contract. No we aren't going to help. No we aren't going to sacrifice an ounce of profit. This is a you problem, but we're being so nice by warning you! Why do you want to stand in the way of progress? What are you a Luddite? We're just saying we're going to take away your ability to pay your mortgage/rent, deny any kids you have a future, and there's nothing you can do about it, why are you anti-progress?"
Cynicism aside, I use LLMs to the marginal degree that they actually help me be more productive at work. But at best this is Web 3.0. The broader "AI vision" really needs to die
As a father of 3, one thing the wife and I had to learn over the course of the first two is that the modern world holds parents to impossible standards and a "fuck off" attitude is required for much of it.
We've had pediatricians shame us for feeding our kids what they're willing to eat and not magically forcing "a more varied diet" down their throats at every meal, despite them being perfectly healthy by every objective metric. There are laws making it technically illegal for us to leave our kids unsupervised at home for any period of time in any condition, even a few minutes if one of us is running slightly late from work/appointments.
Your not-quite-2-year-old is too tall for a rear-facing car-seat? You're a bad parent, possibly a criminal and putting them at risk by flipping the seat to face forward, a responsible parent spends hundreds of dollars they don't have on several different seats to maybe find one that fits better or have their kid ride uncomfortably and arguably unsafely with their legs hyper-extended up the seatback.
Miss a flu shot because you were busy? Careful you don't come off as an antivaxxer.
And all of this and more on top of changing diapers, doctors' appointments, daycare, preschool, school, family activities and full time jobs?
Yeah, when my kids are old enough to engage with social media I will teach them how to use it responsibly, warn them about the dangers, make myself available to them if they have any problems, enforce putting the phones down at dinner and and keep a loose eye on their usage. Fortunately/unfortunately for them they have a technically sophisticated father who knows how to log web activity on the family router without their knowledge. So if anything goes sideways I'll have some hard information to look at. Most families don't have that level of technical skill.
I was almost certainly never going to be a parent for other unrelated reasons, but you have just given me a whole other list of confirmations for that decision that I hadn't thought of before.
Yes and no. Email was designed before the internet had a constant background radiation of SPAM and bullshit, and the network has evolved accordingly.
If you want to deal with the background radiation firsthand that's your prerogative, but it's like growing your own food. Unless you're committed, there's no reason to not just use the grocery store.
I guess if you're in an iterative MVP mindset then this matters less, but that model has always made me a little queasy. I like testing and verifying the crap out of my stuff so that when I hand it off I know it's the best effort I could possibly give.
Relying on AI code denies me the deep knowledge I need to feel that level of pride and confidence. And if I'm going to take the time to read, test and verify the AI code to that level, then I might as well write most of it unless it's really repetitive.
reply