Live data from Hacker News

Software design is now cheap

dottedmag.net

61–70 of 80 posts

Re: Software design is now cheap

#61

Earlier quoted context omitted.

Libraries are more well tested. Unless you "regurgitate code in a library" as "not importing any libraries".

What value is there in tested code when you have the option of superlative, flawless code?

How do you determine flawlessness? How you even approximate a guarantee of it? To what specification is flawlessness judged, and can you precisely and completely relay that spec to your friendly local robot more efficiently than it can vendor / import existing libraries?

Re: Software design is now cheap

#62

Gotta love a world in which a tool which has ingested "all the world's libraries" is now trotted out as a solution to replace those libraries. You know what would happen if all the people who handwrote and maintained those libraries revoked their code from the training datasets and forbid their use by the models? :clown face emoji: This LLM-maxxing is always a myopic one-way argument. The LLMs steal logic from the hu…

LLMs write superior code. Maybe they learned from humans, but they have seen further while standing on those shoulders.

The AI maximalist are really out in force in this thread.

Re: Software design is now cheap

#63

Earlier quoted context omitted.

The value of a library is not just that it does a thing you want, but that it doesn’t do all the things you’d prefer it didn’t. It’s easy to write a cookie parser for a simple case; clearly your robot was able to hand you one for millidollars. How confident are you that you’ve exhaustively specified the exact subset of situations your code is going to encounter, so the missing functionality doesn’t matter? How confid…

My true opinion is that your questions posed here, may become irrelevant in the face of super intelligence

We should probably not be making decisions based on the assumption that super intelligence is coming.

If it does come, nothing we do now really matters. If it doesn’t come and we cash a bunch of checks assuming it will, we are screwed.

Re: Software design is now cheap

#64

Earlier quoted context omitted.

If the LLM writes better code (and it will) then its code should be favored over a library.

People aren’t mentally prepared for the LLMs spitting out flawless code

Because it’s not a forgone conclusion that it’s going to happen in our lifetime.

Re: Software design is now cheap

#65
post #44

Earlier quoted context omitted.

>LLMs are really quite bad at designing anything interesting Let’s be honest, how many devs are actually creating something interesting/unique at their work? Most of the time, our job is just picking the right combination of well-known patterns to make the best possible trade-offs while fulfilling the requirements.

Unless you work for a consulting firm, you should be working on something new/unique. It’s a winner-takes-all market. There are no buyers for off brand Salesforce or Uber.

That feels a bit rigid.

Many people are in position where they can’t afford risking their financial future by going all-in on startup. They just want to do honest work in exchange on paycheck and enjoy time with family after 5pm and on weekends.

Re: Software design is now cheap

#66

Earlier quoted context omitted.

The value of a library is not just that it does a thing you want, but that it doesn’t do all the things you’d prefer it didn’t. It’s easy to write a cookie parser for a simple case; clearly your robot was able to hand you one for millidollars. How confident are you that you’ve exhaustively specified the exact subset of situations your code is going to encounter, so the missing functionality doesn’t matter? How confid…

My true opinion is that your questions posed here, may become irrelevant in the face of super intelligence

I mean ASI could just generate the pixels of a webpage at 60hz. And who needs cookies if ASI knows who you are after seeing half a frame of the dust on your wall, and then knows all the pixels and all the clicks that have transpired across all your interactions with its surfaces. And who needs webpages when ASI can conjure anything on a screen and its robots and drones can deliver any earthly desire at the cost of its inputs. That is if we’re not all made into paper clips or dead fighting for control of the ASML guild at that point.

I say all that mostly in jest, but to take your point somewhat seriously: the most accurate thing you’ve said is that no one is ready for super intelligence. What a great and terrible paroxysm it would be.

Re: Software design is now cheap

#67
I really like the jig analogy. But that the software jig is no different from production software, I don't buy. Saying that the bytes are the same, is like saying that the atoms of a jig is the same as the atoms in the final product.

GenAI generally makes software cheaper. But there is a huge difference in how much. Prototypes and jigs may be 90% cheaper (just making up numbers here), while for production software it may be closer to 10%.

Re: Software design is now cheap

#68

Earlier quoted context omitted.

If AI makes the per line cost of producing software cheaper but you still need an expensive human in the loop then the per line cost is merely cheap not free or at the cost of electricity. Given the choice between A) having one AI produce a library and having 1000 produce code using that library which comes with tests human in the loop vetting documentation and examples which drastically increase the chance of the 10…

This take is just an intermediary take until ai takes over software engineering. In the same way, eventually self driving cars will make human drivers look dangerous I think your thought process is not taking into account what a super logical ai can do, and how effortlessly it could generate some of this code.

> effortlessly

Real question: does your world model suppose super exponential gains in intelligence and efficiency?

Re: Software design is now cheap

#69
post #40

Earlier quoted context omitted.

> Most of the time, our job is just picking the right combination of well-known patterns to make the best possible trade-offs while fulfilling the requirements. Right. I don't trust LLM's to pick the right pattern. It will pick _a_ pattern and it will mostly sorta fulfill the requirements.

Today I asked an LLM (Codex whatever-the-default-is) to implement something straightforward, and it cheerfully implemented it twice , right next to each other, in the same file, and then wrote the actual code that used it and open-coded a stupendously crappy implementation of the same thing right there. The amazing thing is that the whole mess kind of worked.

Right. Kind of works is their MO at the moment. I do try to keep in mind that just because something sucks at the moment, that doesn't mean that it will always suck (especially when you pour _trillions_ of dollars into it)

Re: Software design is now cheap

#70
It's not cheap to develop new large AI models even when one has data. This is where the most interesting software development is. The limitation is because the required hardware is very expensive to buy and also to rent.
Post reply on HN