He's in the files - including photos - and is named by a victim as being present at a "party". It doesn't necessarily mean he did anything untoward but he did fly to the island and attend an event.
Not everyone, just the nounces, like Gates and Brin here. Do you take their defence? Seems like you do. Why would anyone with solid moral values jump to the defence of nounces?
No it is a real question. You have access to EVERYTHING material & service related this world can offer. Why do you also need to torture children and completely ruin their lives?
Their thesis is that code quality does not matter as it is now a cheap commodity. As long as it passes the tests today it's great. If we need to refactor the whole goddamn app tomorrow, no problem, we will just pay up the credits and do it in a few hours.
The fundamental assumption is completely wrong. Code is not a cheap commodity. It is in fact so disastrously expensive that the entire US economy is about to implode while we're unbolting jet engines from old planes to fire up in the parking lots of datacenters for electricity.
It is massively cheaper than an overseas engineer. A cheap engineer can pump out maybe 1000 lines of low quality code in an hour. So like 10k tokens per hour for $50. So best case scenario $5/1000 tokens.
LLMS are charging like $5 per million of tokens. And even if it is subsidized 100x it is still cheaper an order of magnitude than an overseas engineer.
Not to mention speed. An LLM will spit out 1000 lines in seconds, not hours.
I trust my offshore engineers way more than the slop I get from the "AI"s. My team makes my life a lot easier, because I know they know what they are doing. The LLMs, not so much.
Now that entirely depends on app. A lot of software industry is popping out and maintaining relatively simple apps with small differences and customizations per client.
It matters for all the things you’d be able to justify paying a programmer for. What’s about to change is that there will be tons of these little one-off projects that previously nobody could justify paying $150/hr for. A mass democratization of software development. We’ve yet to see what that really looks like.
Side tangent: On one hand I have a subtle fondness for PHP, perhaps because it was the first programming language I ever “learned” (self taught, throwing spaghetti on the wall) back in high school when LAMP stacks were all the rage.
But in retrospect it’s absolutely baffling that mixing raw SQL queries with HTML tag soup wasn’t necessarily uncommon then. Also, I haven’t met many PHP developers that I’d recommend for a PHP job.
php was still fundamentally a programming language you had to learn. This is “I wanted to make a program for my wife to do something she doesn’t have time to do manually” but made quickly with a machine. It’s probably going to do for programming what the Jacquard Loom did for cloth. Make it cheap enough that everyone can have lots of different shirts of their own style.
But the wife didn't do it herself. He still had to do it for her, the author says. I don't think (yet) we're at the point where every person who has an idea for a really good app can make it happen. They'll still need a wozniak, it's just that wozniaks will be a dime a dozen. The php analogy works.
And low-code/no-code (pre-LLMs). Our company spent probably the same amount of dev-time and money on rewriting low-code back to "code" (Python in our case) as it did writing low-code in the first place. LLMs are not quite comparable in damage, but some future maintenance for LLM-code will be needed for sure.
> Their thesis is that code quality does not matter as it is now a cheap commodity.
That's not how I read it. I would say that it's more like "If a human no longer needs to read the code, is it important for it to be readable?"
That is, of course, based on the premise that AI is now capable of both generating and maintaining software projects of this size.
Oh, and it begs another question: are human-readable and AI-readable the same thing? If they're not, it very well could make sense to instruct the model to generate code that prioritizes what matters to LLMs over what matters to humans.
in my experience, what happens is the code base starts to collapse under its own weight. it becomes impossible to fix one thing without breaking another. the coding agent fails to recognize the global scope of the problem and tries local fixes over and over. progress gets slower, new features cost more. all the same problems faced by an inexperienced developer on a greenfield project!
Right, I am a daily user of agentic LLM tools and have this exact problem in one large project that has complex business logic externally dictated by real world requirements out of my control, and let's say, variable quality of legacy code.
I remember when Gemini Pro 3 was the latest hotness and I started to get FOMO seeing demos on X posted to HN showing it one shot-ing all sorts of impressive stuff. So I tried it out for a couple days in Gemini CLI/OpenCode and ran into the exact same pain points I was dealing with using CC/Codex.
Flashy one shot demos of greenfield prompts are a natural hype magnet so get lots of attention, but in my experience aren't particularly useful for evaluating value in complex, legacy projects with tightly bounded requirements that can't be easily reduced to a page or two of prose for a prompt.
I’m well aware, as I said I am regularly using CC/Codex/OC in a variety of projects, and I certainly didn’t claim that can’t be used productively in a large code base.
But that different challenges become apparent that aren’t addressed by examples like this article which tend to focus on narrow, greenfield applications that can be readily rebuilt in one shot.
I already get plenty of value in small side projects that Claude can create in minutes. And while extremely cool, these examples aren’t the kind of “step change” improvement I’d like to see in the area where agentic tools are currently weakest in my daily usage.
I would be much more impressed with implementing new, long-requested features into existing software (that are open to later maintain LLM-generated code).
Fully agreed! That’s the exact kind of thing I was hoping to find when I read the article title, but unfortunately it was really just another “normal AI agent experience” I’ve seen (and built) many examples of before.
Adding capacity to software engineering through LLMs is like adding lanes to a highway — all the new capacity will be utilized.
By getting the LLM to keep changes minimal I’m able to keep quality high while increasing velocity to the point where productivity is limited by my review bandwidth.
I do not fear competition from junior engineers or non-technical people wielding poorly-guided LLMs for sustained development. Nor for prototyping or one offs, for that matter — I’m confident about knowing what to ask for from the LLM and how to ask.
No that has certainly been my experience, but what is going to be the forcing function after a company decides it needs less engineers to go back to hiring?
This is relatively easily fixed with increasing test coverage to near 100% and lifting critical components into model checker space; both approaches were prohibitively expensive before November. They’ll be accepted best practices by the summer.
In ~25 years or so of dealing with large, existing codebases, I've seen time and time again that there's a ton of business value and domain knowledge locked up inside all of that "messy" code. Weird edge cases that weren't well covered in the design, defensive checks and data validations, bolted-on extensions and integrations, etc., etc.
"Just rewrite it" is usually -- not always, but _usually_ -- a sure path to a long, painful migration that usually ends up not quite reproducing the old features/capabilities and adding new bugs and edge cases along the way.
> With a sufficient number of users of an API,
it does not matter what you promise in the contract:
all observable behaviors of your system
will be depended on by somebody.
An LLM rewriting a codebase from scratch is only as good as the spec. If “all observable behaviors” are fair game, the LLM is not going to know which of those behaviors are important.
Furthermore, Spolsky talks about how to do incremental rewrites of legacy code in his post. I’ve done many of these and I expect LLMs will make the next one much easier.
>An LLM rewriting a codebase from scratch is only as good as the spec. If “all observable behaviors” are fair game, the LLM is not going to know which of those behaviors are important.
I've been using LLMs to write docs and specs and they are very very good at it.
That’s a fair point — I agree that LLMs do a good job predicting the documentation that might accompany some code. I feel relieved when I can rely on the LLM to write docs that I only need to edit and review.
But I’m using LLMs regularly and I feel pretty effectively — including Opus 4.5 — and these “they can rewrite your entire codebase” assertions just seem crazy incongruous with my lived experience guiding LLMs to write even individual features bug-free.
When an LLM can rewrite it in 24 hours and fill the missing parts in minutes that argument is hard to defend.
I can vibe code what a dev shop would charge 500k to build and I can solo it in 1-2 weeks. This is the reality today. The code will pass quality checks, the code doesn’t need to be perfect, it doesn’t need to be cleaver it needs to be.
It’s not difficult to see this right? If an LLM can write English it can write Chinese or python.
Then it can run itself, review itself and fix itself.
The cat is out of bag, what it will do to the economy… I don’t see anything positive for regular people. Write some code has turned into prompt some LLM. My phone can outplay the best chess player in the world, are you telling me you think that whatever unbound model anthropic has sitting in their data center can’t out code you?
What mainstream software product do I use on a day to day basis besides Claude?
The ones that continue to survive all build around a platform of services, MSO, Adobe, etc.
Most enterprise product offerings, platform solutions, proprietary data access, proprietary / well accepted implementation. But lets not confuse it with the ability to clone it, it doesnt seem far fetched to get 10 people together and vibe out a full slack replacement in a few weeks.
If an LLM wrote the whole project last week and it already requires a full rewrite, what makes you think that the quality of that rewrite will be significantly higher, and that it will address all of the issues? Sure, it's all probabilistic so there's probably a nonzero chance for it to stumble into something where all the moving parts are moving correctly, but to me it feels like with our current tech, these odds continue shrinking as you toss on more requirements and features, like any mature project. It's like really early LLMs where if they just couldn't parse what you wanted, past a certain point you could've regenerated the output a million times and nothing would change.
The whole point of good engineering was not about just hitting the hard specs, but also have extendable, readable, maintainable code.
But if today it’s so cheap to generate new code that meets updated specs, why care about the quality of the code itself?
Maybe the engineering work today is to review specs and tests and let LLMs do whatever behind the scenes to hit the specs. If the specs change, just start from scratch.
"Write the specs and let the outsourced labor hit them" is not a new tale.
Let's assume the LLM agents can write tests for, and hit, specs better and cheaper than the outsourced offshore teams could.
So let's assume now you can have a working product that hits your spec without understanding the code. How many bugs and security vulnerabilities have slipped through "well tested" code because of edge cases of certain input/state combinations? Ok, throw an LLM at the codebase to scan for vulnerabilities; ok, throw another one at it to ensure no nasty side effects of the changes that one made; ok, add some functionality and a new set of tests and let it churn through a bunch of gross code changes needed to bolt that functionality into the pile of spaghetti...
How long do you want your critical business logic relying on not-understood code with "100% coverage" (of lines of code and spec'd features) but super-low coverage of actual possible combinations of input+machine+system state? How big can that codebase get before "rewrite the entire world to pass all the existing specs and tests" starts getting very very very slow?
We've learned MANY hard lessons about security, extensibility, and maintainability of multi-million-LOC-or-larger long-lived business systems and those don't go away just because you're no longer reading the code that's making you the money. They might even get more urgent. Is there perhaps a reason Google and Amazon didn't just hire 10x the number of people at 1/10th the salary to replace the vast majority of their engineering teams year ago?
> let LLMs do whatever behind the scenes to hit the specs
assuming for the sake of argument that's completely true, then what happens to "competitive advantage" in this scenario?
it gets me thinking: if anyone can vibe from spec, whats stopping company a (or even user a) from telling an llm agent "duplicate every aspect of this service in python and deploy it to my aws account xyz"...
It’s all fun and games vibecoding until you
A) have customers who depend on your product
B) it breaks or the one person prompting and has access to the servers and api keys gets incapacited (or just bored).
Sure we can vibecode oneoff projects that does something useful (my fav is browser extensions) but as soon as we ask others to use our code on a regular basis the technical debt clock starts running. And we all know how fast dependencies in a project breaks.
Walmart, McDonalds, Nike - none really have any secrets about what they do. There is nothing stopping someone from copying them - except that businesses are big, unwieldy things.
When software becomes cheap companies compete on their support. We see this for Open Source software now.
These are businesses with extra-large capital requirements. You ain't replicating them, because you don't have the money, and they can easily strangle you with their money as you start out.
Software is different, you need very very little to start, historically just your own skills and time. Thes latter two may see some changes with LLMs.
I don't see the relevance to the discussion. Marketing is not significantly different for a shop and a online-only business.
Having to buy a large property, fulfilling every law, etc is materially different than buying a laptop and renting a cloud instance. Almost everyone has the material capacity to do the latter, but almost no one has the privilege for the former.
I think `andrekandre is right in this hypothetical.
Who'd pay for brand new Photoshop with a couple new features and improvements if LLM-cloned Photoshop-from-three-months-ago is free?
The first few iterations of this cloud be massively consumer friendly for anything without serious cloud infra costs. Cheap clones all around. Like generic drugs but without the cartel-like control of manufacturing.
Business after that would be dramatically different, though. Differentiating yourself from the willing-to-do-it-for-near-zero-margin competitors to produce something new to bring in money starts to get very hard. Can you provide better customer support? That could be hard, everyone's gonna have a pretty high baseline LLM-support-agent already... and hiring real people instead could dramatically increase the price difference you're trying to justify... Similarly for marketing or outreach etc; how are you going to cut through the AI-agent-generated copycat spam that's gonna be pounding everyone when everyone and their dog has a clone of popular software and services?
Photoshop type things are probably a really good candidate for disruption like that because to a large extent every feature is independent. The noise reduction tool doesn't need API or SDK deps on the layer-opacity tool, for instance. If all your features are LLM balls of shit that doesn't necessarily reduce your ability to add new ones next to them, unlike in a more relational-database-based web app with cross-table/model dependencies, etc.
And in this "try out any new idea cheaply and throw crap against the wall and see what sticks" world "product managers" and "idea people" etc are all pretty fucked. Some of the infinite monkeys are going to periodically hit to gain temporary advantage, but good luck finding someone to pay you to be a "product visionary" in a world where any feature can be rolled out and tested in the market by a random dev in hours or days.
OK, so what do people do? What do people need? People still need to eat, people get married and die, and all of the things surrounding that, all sorts of health related stuff. Nightlife events. Insurance. actuaries. Raising babies. What do you spend your fun money on?
People pay for things they use. If bespoke software is a thing you pick up at the mall at a kiosk next to Target we gotta figure something out.
Even if specialized robots were at parity with specialized people (they are not in dimensions like dexterity), the big thing missing is the flexibility. You can on the fly change the production process, humans will be able to accommodate the changes (not at perfect speed, but still). For specialized robots you need stop and reprogram them.
I don't know why people think that legs automatically make everything more flexible. It boggles the mind.
Look at real flexible manufacturing systems to see how much of a bullshit idea that is: https://youtu.be/gUvE2eFH6CY
Everything is transported via the central stacker crane that is directly connected to every machine. You don't need legs. This just leaves the arms and here is the thing, you can just have two robot arms in the same robot cell and call it a day. The humanoid form factor adds nothing.
Also what makes you think you don't have to program the humanoid robots? Again, everyone seems to think that if you build a human shaped robot, human level intelligence will automatically come as a result of the shape of the robot. The moment you remove the head, the intelligence vanishes.
The only real advantage is that you have access to a UI—ish everywhere, because the ssh server is running everywhere by default (at least at machines you would want to connect to).
Http servers are not installed by default, and they are a pita to configure / secure.
For one the whole country of Ukraine is fighting like hell for almost 4 years following the orders of their elected government to defend their country.
If Russia was on the right, the people of Ukraine would have just hanged Zelenskyy and his gov, instead of sending their children to the meat grinder.
Let’s see if Venezuelans will put their lives on the line to protect the regime.
Military (or part of) can (and historically does) initiate a coup. If civilians are also on board the gov is over in hours. Coups typically fail when people are not on the same page.
Turkey is a great example. Heck Putin also had Wagner knocking his door in Moscow.
Lyft is also a scam for the drivers. In a ride from the airport to home during rush hour (1h and 15 minutes drive) I got charged ~$140. The company was paying, so whatever.
During the ride I was chatting with the driver, and I was curious how much he was making from the ride.
At the end of the ride he showed me. $48 (before my tip). WTF.
From that he had to pay gas, maintenance and taxes.
How is this legal? What is the marginal cost for Lyft per mile driven? It must be close to zero. Insane.
I know plenty of Uber (and normal taxis) drivers around the airport here who pick up a someone, then ask if they mind taking someone else. Because it is usually vans and business customers, they don't care and actually kind of like talking with other business guys who probably went or are going to the same seminar/conference etc. The driver will then load up whatever fits who are waiting for taxis or drivers and only report 1 person to the service. As this is hotel to airport to hotel, there are not many ways of uber, lyft etc detecting this unless someone rats them out. I asked a driver and obviously he responded with Uber screws me, I screw Uber.
In Vietnam, if you see a parked driver waiting for a call, you can show him your Grab (ie, Asian copy of Uber) price to go somewhere, then get the same ride for 80%.
A similar thing happened to me in South America while on vacation, I was looking to book an Uber but the taxi driver gave me a small discount to do it "on the side" and explained that he wouldn't see most of the money from Uber.
As a passenger, the advantage of Uber is that if something happens, I have someone accountable: drive + car plate. But in reality I don't know if that works
Many normal taxis drive also for Uber or Lyft as you need the license anyway over here. Not sure if you can be Uber AND Lyft at the same time.
Payment is preferably cash (I started wearing cash again with how the lovely cashless stuff is ramping up here in the EU), but I had all drivers so far who simply had this Square like device on their phone to take payments. So the driver runs around to let out the 'main' passenger, let's them walk off, runs around to open the van door and tell what the price is cash or tap your card. That is the most common. I see sometimes they charge similar to what the 'main passenger' pays and sometimes less.
How does this compare to typical taxi corporations? In Europe at least, taxis are often organised into companies, with centralised bookings, and taxi drivers paying a cut to the corporation. Here the cut is, based on your numbers, 65%, which does seem very high, but then what do I know.
I believe taxi companies own the license (which is super expensive) as well as the car. They also pay maintenance and gas costs. So 35% cut to just drive equipment is not that bad. The issue with uber/lyft is that you also need to bring your vehicle, pay maintenance, gas, insurance and depreciation.
I think that poor guy made less than 15% (assuming an 80 cent per mile cost for the vehicle).
I believe in Europe taxi drivers typically cover these costs too. Not sure about licensing costs. In that regard, they are more like cooperatives rather than "companies with employees". But I don't know for sure - and probably varies by locale.
Looking at the financials of Lyft, based on what they report gross bookings are ~ 4.8B. 3B are driver earnings and 1.8B is the Lyft portion. So on average Lyft is getting 37%. Maybe they subsidize the shorter rides with the longer ones.
Lyft is software. Marginal cost is almost always close to zero for software but it hardly matters, software like that has high R&D + marketing costs. It's not like Lyft just magically appeared. Uber took many years to become profitable because their costs were so high, Lyft is probably the same.
The IRS mileage cost of 0.70/mi is for a car in a situation that an Uber driver should never be in, that is, an average car with average fuel economy being professionally serviced and maintained, with average depreciation and interest rate. None of those should be the case for anyone driving Uber.
But that was the lure of ridesharing. Bring your own average car, no need to buy special equipment.
If you do have to buy a car just for uber, then you would have to consider the interest payments as additional cost (not just the depreciation of the equipment, which will be super brutal for a brand new car).
In any case, you are looking at something north of 50 cents per mile.
Um, I think you're taking my comment reversed. Using a new car for Uber is what you should never do. You should be using the shittiest car possible. Buying a new car for Uber is not good. The cost per mile, as calculated by IRS, goes up with a new car because that cost includes depreciation and interest. The cost is not actually that high if your car is old.
They have their own internal market, which now has a middle class equal in size to the entire US population.
They have all of Asia, with a market of another ~2B, and a completely undeveloped market in Africa of another 1B people.
That's part of what the Chinese Belt and Road Initiative is, an industrial policy to establish trade links and infrastructure dependencies across the world that uses Chinese direct FDI and industrial policy to establish new markets for their own industries.
Which is exactly the same policy that the US adopted as part of the Marshall Plan and its use (up until 2025) of soft power to promote US FDI across the world.
It's the US that is dependent on a defense industry and foreign sales for its industrial capacity.
That's why the US defense budget is 50% of the total and over USD1T/year and is why the US is demanding that NATO nations buy US defense equipment.
Yeah, there are some theories that state that WWI and WWII started because of over production and the search for new markets (I saw a video recently mentioning some books, including one from Lenin), so you might be in to something
Hybrids and EV, at least in Spain both are quickly becoming popular, even with tariffs. Probably helps that our government still gives people ~3K EUR if they go electric.
It varies by company. The companies that participated in the audit generally got hit with a 17% tariff, the ones that didn't, 34%. (oversimplified).
Either way I phrased my original comment as a question as I'm not sure whether to consider 17% or 34% as "high". It depends on perspective. Both are painful, but neither are high enough to completely kill trade, like 100%+ tariffs do.
reply