For the best experience on desktop, install the Chrome extension to track your reading on news.ycombinator.com
Hacker Newsnew | past | comments | ask | show | jobs | submit | history | inimino's commentsregister

And you thought your decision to not1 read the article was worth sharing why?

At least Wolfram's ego led him to contribute something interesting.


It’s called “being the change you want to see”. I want to see less ego, so I’m telling those who are the opposite that it has downsides.


FYI, "be the change you want to see" is approximately the golden rule "do unto others". If you want less ego in the world, demonstrate it yourself. It does not mean "complain about how other people act".


I said I want to _see_ less ego. Calling out assholes is being that change, because not enough people do it. If you’re going to try and feel superior through technicality (which let’s be honest, claiming a single interpretation of a common phrase is a dumb way of trying to achieve that), at least pay attention to the details.


The pure evil of these purity tests is fully on display and as repulsive as ever.


Insane thing to write when the "purity test" is not supporting/investing in a defense contractor with a CEO who begged Epstein to go to the island.


This research process is the same as what I've been doing.

https://cmpr.ai/hutter/archive/

Claude does the research, like having an army of very fast but forgetful grad students working for free.

The individual paper doesn't make much incremental improvement but once you get a pipeline of results building in a particular direction it's powerful.


So many words to say "it predicts the later tokens in light of those already emitted."


Literally nothing about her purple hair and her outfit is goth in any way shape or form so it's interesting that people are latching onto that.


Goth culture has changed a lot, it's no longer all black and white (literally) like it was in the 90s. And I see purple hair a lot. But yeah the rest of her outfit doesn't match. I only had two images to go by :)


SCP anti-memetics division.


Nobody is going to maintain it, the spec that generated it will be given to better systems and it will be rewritten.


That would be possible if you had just the spec, but after sometime most of the code will not have been generated through the original spec, but through lots of back and forth for adding features and big fixing. No way to run all that again.

Not that old big non-AI software doesn't have similar maintainability issues (I keep posting this example, but I don't actually want to callthat company out specifically, the problem is widespread: https://news.ycombinator.com/item?id=18442941).

That's why I'm reluctant to complain about the AI code issues too much. The problem of how software is written, on the higher level, the teams, the decisions, the rotating programmers, may be bigger than that of any particular technology or person actually writing the code.

I remember a company where I looked at a contractor job, they wanted me to fix a lot of code they had received from their Eastern European programmers. They complained about them a lot in our meeting. However, after hearing them out I was convinced the problem was not the people generating the code, but the ones above them who failed to provide them with accurate specs and clear guidance, and got surprised at the very end that it did not work as expected.

Similar with AI. It may be hard to disentangle what is project management, what is actually the fault of the AI. I found that you can live with pockets of suboptimal but mostly working code well enough, even adding features and fixing bugs easily, if the overall architecture is solid, and components are well isolated.

That is why I don't worry too much about the complaints here about bad error checks and other small stuff. Even if it is bad, you will have lots of such issues in typical large corporate projects, even with competent people. That's because programmers keep changing, management focuses on features over anything else (usually customers, internal or external, don't pay for code reorg, only for new features). The layers above the low level code are more important in deciding if the project is and remains viable.

From what the commenters say, it seems to me the problem starts much higher than the Claude code, so it is hard to say how much at fault AI generated code actually is IMHO. Whether you have inexperienced juniors or an AI producing code, you need solid project lead and architecture layers above the lines of code first of all.


That's why all the code in my project is generated from the "prompts" (actually just regular block comments + references) and so all of that is checked in.


This really feels like a faith-based argument. That's not possible today

I'd much rather make plans based on reality


I've been living this reality for months and built a tool around this workflow so no faith required.


...if anyone.


Good point. They might not know why either.


you can snapshot layer activations any time you want...


self-aware, an LLM isn't but a thinking model can be a little bit


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

Search:

HN For You