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

> The more code AI writes for me the worse it gets.

That makes no sense unless you're claiming that the models are getting worse at writing code.

> Either AI gets smart enough that it won’t matter in the future or we’re going to have a huge mess to clean up.

My prediction is that both will happen.


> That makes no sense unless you're claiming that the models are getting worse at writing code.

A hypothetical scenario is it needs to add two numbers so it writes add(x,y).

Later on it needs to add three numbers so it writes add(x, y, z)

Then it needs to add four…

Layers upon layers. A human would likely notice the pattern and refactor so add accepts a list.


My experience is that the LLM offers that approach from the get-go.

Also, I've worked with lots of humans who sadly would not notice the pattern.


They are priced out earlier - when they can't get the academic credentials to pass the medical school gatekeeping.

You mean they can’t get an undergraduate degree. That’s a different problem.

Same with politicians.

Prompts and LLM conversations have now become an important software artifact. I don't think the question should be whether or not to save them. They should be saved. The question is how to structure them in your folders and whether or not they should be part of the context for the LLM.

Our approach is to save LLM conversations but to not have them be part of the context.


Do you think it is equally important to save complete transcripts of your deliberations with coworkers? If not, why not?

> have now become an important software artifact

have they though? I feel like 50% of the chat history is gettin in the way of the model that just created it half the time, let alone any future LLM.

Humans wont re-read an old chat history either unless very desperate for clues.

The few valuable nuggets of information in the chat history can probably be summarize into 3 bullet points and put in the docs or in code comments.

I really dont see the value.


I think the question is still valid what you actually do with them once they are saved.

Software engineers do code reviews, and in the age of AI, they have to do chat reviews.

Much of the knowledge of writing the software is manifest and captured in those chats. and we share them so that we can learn from each other.


Obviously, that's the correct end result. We're just not quite there yet.

yet is extremely load-bearing here.

Like people talking about typos not substance when discussing a subject and have nothing better to add.. annoying

Private autonomous transportation will allow that public infrastructure to be tenfold more productive.

Public transportation will never have the incentive to minimize cost and headcount.

Where we do have public transportation, it should always face competition from private offerings - including on the tracks, as they do in Italy, for example.


That's not true. For example, France is rapidly automating its metros. The US is quite unique in viewing public transport as a jobs program rather than a public service.

Of course it has the incentive. Even in this thread people are getting mad about it costing too much.

When someone says incentive in this context, they usually mean the individual incentives of each of the workers to make money for themselves, get promoted to get a share of profit, not the overall fuzzy public pressure.

Sound Transit still uses this strategy in Seattle region.

They really don't. They don't build residential or commercial property.

I assume my daughter used that song as well. I remember us sitting at the dining room table and her peeling off 100 digits of pi. I explained to her that that would provide an accuracy such that a circle the size of the observable universe would be accurate to within a Planck length.

Fun memory from 16 years ago. Next month she'll be obtaining her PhD in physics.


I don't even get the "quality hardware" argument. The only hardware I interact with is my high quality mechanical keyboard, trackball, and color calibrated monitor. All are vastly superior to any Apple hardware that I would interact with.

It's mostly about laptops. Most people use laptops. Apple laptops are good and all the other ones are bad.

> Apple laptops are good and all the other ones are bad.

Bad or not as good?

For many people not as good can be good enough.

For instance I am mostly working from home, and will never spend more than 6 hours straight without a pause nor do I work "on the road" so I never cared about having a +11h of battery life. I understand it can be very valuable in some circonstances but it has never been a thing for me and for many people using their laptop mostly at home. I wouldn't trade having a forced siri install or the shitty keyboard that used to come with macbook a few years ago for more battery life than I actually need.


I didn't really interpret this discussion as being about laptops - as opposed to being around Apple hardware and software in general.

It's obviously not about the desktop setting.

It's a valid assumption, and it is going to have a huge impact on the SaaS marketplace. "I need a resource tracking application. Let me find a consultant to help me vibe code it rather than pay $10,000 a month."

Hiring a consultant to vibe code isnt the same as a non technical vibe coder, the whole point he's making.

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

Search: