Hacker Newsnew | past | comments | ask | show | jobs | submit | lbreakjai's commentslogin

Not if your customer base can't afford to eat your food because they lost their jobs to AI.

This sounds horrible. Onboarding should ideally be marginally about the "what". After all, we already have a very precise and non ambiguous system to tell what the system does: the code.

What I want to know when I join a company is "why" the system does what it does. Sure, give me pointers, some overview of how the code is structured, that always helps, but if you don't tell me why how am I supposed to work?

$currentCompany has the best documentation I've seen in my career. It's been spun off from a larger company, from people collaborating asynchronously and remotely whenever they had some capacity.

No matter how diligent we've been, as soon as the company started in earnest and we got people fully dedicated to it, there's been a ton of small decisions that happened during a quick call, or on a slack thread, or as a comment on a figma design.

This is the sort of "you had to be there" context the onboarding should aim to explain, and I don't see how LLMs help with that.


Because it most certainly is.

I drive a 2014 Ford Fiesta. Every car feels huge in comparison. I had a Nissan Qashqai parked next to my car, it looked like a tank. I had a look inside, it didn't seem particularly spacious.

Same when I flew to Bilbao. I booked late, the only rentals left were in the luxury segment. I drove off in a mild-hybrid Lexus NX, where I struggled to fit the luggage that fit reasonably well in the boot of my car on the way to Schiphol.


Why not just ban cars in the cities instead? The problem is those who need cars the most are those who can't afford to live in the city centers, so it often ends up being an extra tax in the less affluent.

People that need cars don't tend to have large cars, unless there's some tax benefits (someone in the village has one of those 5 seater dumper trucks because they can write it off as a business expense but can't write off a Toyota Aygo or Citroen C1 which would far more sensible)

That doesn't align with my experience. I grew up in Belgium, in a place where you'd be lucky to have a bus an hour. The closest place to get groceries, by foot, was half an hour away, most of it 5% uphill on the way back.

If you need a car, then you need it for everything. You need to be able to fit the two kids you picked at school, the gear for the sport activity you'll drop them at, the mom you picked at the train station after work, and the weekly groceries you picked from the supermarket on your way back. From experience, you aren't doing all of that in a Hyundai i10.

Now I live in the Randstad. Groceries get delivered, mom rides the bus for 8 minutes to come back home, and I pick the kid by bike. The car is optional and pure convenience, so I can get away with a small one.


A bus an hour, surely you mean a bus a week?

We have two cars, one 1.6m, one 1.7m, and handle all that. A Hyundai i10 is 1.68m wide.

A Range Rover is 2 metres wide. Ridiculous size and completely unnecessary in rural areas, I assume they are needed in towns.


A Range Rover is conspicuous consumption, not transportation.

For some reason we decided to put a great deal of jobs in the city centers. Commuting to the edge of a city and then taking public transport to office doesn't really work, unless massive amounts of money are pumped into trains, busses and trams.

There's this weird perception that Europe has excellent public transport, while in reality it only works, sort of, in a few larger cities. Everywhere else functioning in society really requires a car or assumes that you're living within biking distance of work and daycare.


I worked on the migration to Azure for the big orange one. They absolutely went all-in on it.

Because it implicitly suggests that 99% of the visitors are happy with the website. Without knowing the number of unique visitors during that month, and the number of people that complained, this is meaningless.


That's why I don't get people that claim to be letting an agent run for an hour on some task. LLMs tend to do so many small errors like that, that are so hard to catch if you aren't super careful.

I wouldn't want to have to review the output of an agent going wild for an hour.


The agent reviews the code. The agent has access to tools. It writes the code, runs it through a test, reads the error, fixes the code, keeps going. It passes the code off to another agent with a prompt to review code and give it notes. They pass it back and forth, another agent reads and creates documentation. It keeps going and passes things back.

Now that's the idea anyway. Of course they all will lie to each other and there's hallucinations every step of the way. If you want to see a great example look at the documentation for the TEMU marketplace API. The whole API system, docs, examples etc appears to be vibe coded and lots of nonsensical formatting, methods that don't work and parameters in example that just say "test" or "parameters", but they are presented as working examples with actual response examples (like a normal API) but it largely appears to just be made up!


Who says anyone’s reviewing anything? I’m seeing more and more influencers and YouTubers playing engineer or just buying an app from an overseas app farm. Do you think anyone in that chain gives the first shit what the code is like?

It’s the worst kind of disposable software.


Humans are very capable of creating bugs. This in itself is not a tell.


It could be worse. You could have a backup on Azure.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: