I think it depends on what you find enjoyable. I think people who like the tinkering and the actual act of coding, debugging, etc. will find it less and less fun to be in this area, but people who like to look at the big picture, and solve problems, will see that they will now be better at both getting overview of larger and larger codebases and that technical debt that was never attainable to solve before can now be “outsourced” to LLM’s.
I find that fun. I work in a 50 year old IT company, with lots of legacy code and technical debt which we have never been able to address - suddenly it’s within reach to really get us to a better place.
The best way to have a big picture view of a project is to build a mental model of that project in your head. Coding with LLMs removes that ability, and replaces it with an illusion.
Well if you have experience reviewing other people’s code, it is not that different than finding an idea, asking copilot to do it, and then review just as if you had a ton of junior engineers to write code for you, which also can go too far in one direction before asking for feedback.
So it really depends on your reviewing ability how maintainable code you will get. It is a bit of effort to review something “you have done” as thoroughly as something a colleague have done. Somehow I still feel sense of ownership even though the LLM did it.
I like reviewing using GitHub’s interface, so I often do a thorough review in that familiar interface while the PR is still draft, and before I have invited others to review. If I review my own code directly in my editor when the agent is done, my brain isn’t in the right context and can get distracted or skip over something.
Does the thing work like I want it in the end? Is it fast, reliable, enjoyable to use, maintainable, cheap, efficient, resilient, etc?
If so, I don't care if I wrote it by hand or with an LLM. People who think that building something with an LLM somehow dooms the something to mediocrity are engaging in magical thinking. I can simply use as much or as little LLM as will allow me to meet my quality criteria.
You listed "maintainable", but how do you know your project is maintainable, if you yourself have no understanding of the code base? Presumably the reason is that the AI has managed to maintain the project so far, so it follows that it will be able to do so in the future. But that's not a given. It's more of a prayer.
Exactly this. I use agents every day to either produce tests for code I've written according to the guidelines I set out for it, or to produce the boilerplate code (which is seldom enjoyable) before I get to add the cool stuff.
Furthermore, when I inevitably get stuck on a thornier section of new code, or revisiting a codebase which I've not investigated for some time, I can use the agent to provide ideas and suggestions of where/how to start/get unstuck.
Like any tool - it's how you apply it to the job in hand (and ensuring the job is relevant) that counts.
One way of framing this is that people that prefer to solve problems are actually bad at tinkering and writing good code. Hence the existence of terrible codebases written by devs thet “liked to solve problems for the customers”.
It is not that clear cut that problem-solvers have that in addition to the tinkering part nor it is guaranteed that tinkerers don’t like to solve problems.
Two independent axis!
I'm as nerdy as they come (my current project is the fourth compiler I've worked on), and I absolutely love this new way of working. There's a lot more time spent in discussion with the agent (an extremely frustrating discussion, to be fair). All of a sudden, there's an extremely high payoff to investing in good fundamentals (namely, clarity of requirements, good tools, etc.), which are the things I want to invest in anyway! If you get these fundamentals right, you can let the agent rip and produce hundreds of PRs that are correct, or create workflows that are actually not slop or ship code that is, while not yet as high quality as if you wrote it manually, quite close, at easily five times the speed.
And throughout this, if I'm ever curious about how the ideas relate to some other topic, I can just ask the agent, "Are we designing XYZ right now? Categorically, is it this?" Lots of really cool discussions to be had.
I might be less enthusiastic if I was just shipping CSS changes and the like.
I have been trying this as well, and you can quickly come very far.
However, I fear that agents will always work better on programming languages they have been heavily trained on, so for an agent-based development inventing a new domain specific language (e.g. for use internally in a company) might not be as efficient as using a generic programming language that models are already trained on and then just live with the extra boilerplate necessary.
Eventually the models will be generally be so good that the competition moves from the best model to the best user experience and here I think we can expect others will win, e.g. Microsoft with GitHub and VS Code
That's my hope but Google has unlimited cash to throw at model development and can basically burn more cash can openai and anthropic combined. Might tip the scale in the long run.
You still have to synchronize with your code reviewers and teammates, so how well you work together in a team becomes a limiting factor at some point then I guess.
Yes, and that constraint shows up surprisingly early.
Even if you eliminate model latency and keep yourself fully in sync via a tight human-in-the-loop workflow, the shared mental model of the team still advances at human speed. Code review, design discussion, and trust-building are all bandwidth-limited in ways that do not benefit much from faster generation.
There is also an asymmetry: local flow can be optimized aggressively, but collaboration introduces checkpoints. Reviewers need time to reconstruct intent, not just verify correctness. If the rate of change exceeds the team’s ability to form that understanding, friction increases: longer reviews, more rework, or a tendency to rubber-stamp changes.
This suggests a practical ceiling where individual "power coding" outpaces team coherence. Past that point, gains need to come from improving shared artifacts rather than raw output: clearer commit structure, smaller diffs, stronger invariants, better automated tests, and more explicit design notes. In other words, the limiting factor shifts from generation speed to synchronization quality across humans.
I've seen this happen over and over again well before LLMs, when teams are sufficiently "code focused" that they don't care much at all about their teammates. The kind that would throw a giant architectural changes over a weekend. You then get to either freeze a person for days, or end up with codebases nobody remembers, because the bigger architectural changes are secret.
With a good modern setup, everyone can be that "productive", and the only thing that keeps a project coherent is if the original design holds, therefore making rearchitecture a very rare event. It will also push us to have smaller teams in general, just because the idea of anyone managing a project with, say, 8 developers writing a codebase at full speed seems impossible, just like it was when we added enough high performance, talented people to a project. It's just harder to keep coherence.
You can see this risk mentioned in The Mythical Man Month already. The idea of "The Surgery Team", where in practice you only have a couple of people truly owning a codebase, and most of the work we used to hand juniors just being done via AI. It'd be quite funny if the way we have to change our team organization moves towards old recommendations.
I've mostly done solo work, or very small teams with clear separation of concerns. But this reads as less of a case against power coding, and more of a case against teams!
You can ask the agent to reverse engineer its own design and provide a design document that can inform the code review discussion. Plus, hopefully human code review would only occur after several rounds of the agent refactoring its own one-shot slop into something that's up to near-human standards of surveyability and maintainability.
Trump doesn’t understand that Greenland is a ~country~ self-gorverning territory in itself in the Kingdom of Denmark. Just like Australia is country in itself in the Commonwealth.
England would never be able to sell Australia to the US, just as we in Denmark are not able to sell Greenland.
The only way forward is trade war it seems and it would be better to escalate it quickly in order for Trump to understand the message.
> Just like Australia is country in itself in the Commonwealth.
That’s really not even close. Greenland isn’t even remotely self sustainable without Danish funding. It also has MPs in the Danish parliament. So yes while it technically has self-rule it’s still effectively a colony
I’m just trying to explain how absurd the proposition is seen from a Danish perspective, and why we from Danish side will continue to say no, as and refer to the same thing as our PM’s have said again and again: this is for Greenlandic people to decide. They would have to vote for it, but all the parties in Greenland are against joining the US.
So whatever proposal or threat of breaking down NATO that Trump will come up with will be met with a no from Danish politicians. It is simply not for them to decide. His only option seen from a Danish perspective is to use the military.
Puerto Rico is not a country, today, but is analogous to Greenland. They could vote to become closer to the US or vote to distance themselves. Similar to all less-than-independent regions held by larger countries. Remnants of the age of exploration or before, or the crumbs left from wars.
Pushing the me-strong logic to the (absurd?) limit, why isn’t California a country? Or New England? Or the red state swath of the US?
Do they realize who actually lives in Greenland and that it’s not green? Or do they think they’ll just deport them all back to where they came from (sigh) and warm the place up?
Greenlanders could vote to be completely independent, yes. That is the situation right now.
However, Trump has done everything to turn Greenlanders away, and not done anything to convince them of independence would be good for them, so a vote for independence will likely fail catastrophically right now. Independence is many decades away, as they would really have to build a stronger economy to make it happen, but that is the direction Greenlanders would like to go, at least if you asked them 2 years ago.
The "independence" of Greenland under Trump would be identical to the "independence" of Venezuela following the US' abduction of its leader & murder of 100 people during the operation. Whatever Greenland's opinion on independence is, what's on offer by Trump would only be worse in every way than what they currently have.
Not in a meaningful way which Greenlanders would submit to. There would be constant unrest and civil disobedience, nothing would function, and bringing in your own people (including the armed forces) to keep things barely working wouldn't be a solution either.
Unfortunately Greenland as a whole has 50.000 people in total of which 20.000 live in largest city and the rest scattered across 19 others.
Thats about the size of a small town in the US, the country may be big in territory but not in population.
It happens all the time. America and the EU are bought and paid for. The funniest part is that they’re being paid for with the very money the buyers plunder with the left hand, only to use the right hand to purchase the treasonous dominant class.
It’s like a sleight of hand magic trick pulled on an infant that is then gleeful for the deception.
You can even become your own kingdom (see california, Hawaii, texas, ...) before becoming part of another kingdom.
It may not be straightforward, however; as Linebarger states:
> Formally, war may be defined as the "reciprocal application of violence by public, armed bodies."
> If it is not reciprocal, it is not war, the killing of persons who do not defend themselves is not war, but slaughter, massacre, or punishment.
> If the bodies involved are not public, their violence is not war. Even our enemies in World War II were relatively careful about this distinction, because they did not know how soon or easily a violation of the rules might be scored against them. To be public, the combatants need not be legal—that is, constitutionally set up; it suffices, according to international usage, for the fighters to have a reasonable minimum of numbers, some kind of identification, and a purpose which is political. If you shoot your neighbor, you will be committing mere murder; but if you gather twenty or thirty friends, together, tie a red handkerchief around the left arm of each man, announce that you are out to overthrow the government of the United States, and then shoot your neighbor as a counterrevolutionary impediment to the new order of things, you can have the satisfaction of having waged war. (In practical terms, this means that you will be put to death for treason and rebellion, not merely for murder.)
> ...
Note that this advice was from the mid-XX; in the XXI not all kingdoms seem to recognise the Geneva Conventions anymore!
These days it's probably a case of conjugating irregular verbs?
I am a (dissident turned) freedom fighter
You are a (perfidious) combatant
They are (drug-running) terrorists
Sadly we, the "good guys", created a dangerous precedent in the balkans when Kosovo unilaterally split from Serbia, under foreign (NATO) occupation moreover.
International law does not promote nor support unilateral secessions. If a region or autonomous republic wants to secede it should only do so in accordance to the host country laws. E.g. the Quebec and Scotland referendums were made in accordance to the host countries of Canada and UK.
But then we created that dangerous case where now every region can secede from their host one unilaterally, even if it's occupied by foreign forces. And in practice, the "legality" of it, really depends on international recognition and the undergoing narratives.
International laws have always been pleasantries, as there's no real ways to enforce them, but there were powerful incentives for everybody to play by the rules.
It's hardly a precedent, probably half of the countries worldwide have been formed by seceding from some other country against its will. U.S. would be in this half.
It's the first country to do so under foreign military presence since UN inception.
The only precedents of unilateral secession were Slovenia and Croatia from Yugoslavia and Bangladesh from Pakistan but none did so under foreign military presence.
All of the Arab countries have basically seceded from Ottoman empire under an occupation of this or that European country.
"Unilaterally" is not easy to define. Sometimes there is a long and violent struggle for independence and the metropole eventually gives in and signs some paper, sometimes it is stubborn and doesn't sign anything - the difference is not that important in my opinion.
Literally Hitler is murdering civilians in broad daylight and threatening to start WW3 by invading friendly territories! Oh but also, we should stay calm and issue strongly worded statements and trade declarations.
This is an incoherent position. If the threat is as real as claimed, a simple weapon test should be merited. France's official nuclear doctrine permits first strikes anyway.
Literally Hitler is murdering civilians in broad daylight
That is for Americans themselves rise up against. The rest of the world can decide to sanction this behavior, etc. But nations are sovereign.
by invading friendly territories!
We are still in the I am going to tariff you, because I want to buy Greenland-stage. Sure, he has threatened to invade Greenland if that fails, but that's why it is important to make the US feel the pain by employing (initially parts of) the trade bazooka. Then US citizens, congress, the brolichargy or however feels hurt can try to put the government back in check.
Don't forget that for a lot of US tech companies, the EU is the second largest market. Losing control of that hurts the Microsofts, Metas, and Amazons of this world enormously. Some already get nervous without the tariffs or counter-measures started:
Soon dollars might not be accepted if US companies wants to buy things in the EU, they will have to pay in euros (part of the anti coercion instrument that Macron and others have been talking about the last couple of days)
I don't think it will happen. 10% of EU bank loans that are dollar-denominated [0]. If they cut the flow of dollars into the EU, the debtors of those loans would wind up offering a premium for their goods and services to non-US companies, making them uncompetitive. It would be a roundabout tariff that would hurt the EU countries too much.
I find that fun. I work in a 50 year old IT company, with lots of legacy code and technical debt which we have never been able to address - suddenly it’s within reach to really get us to a better place.
reply