If your build scripts are more than 100-300 LOC you are doing something very wrong.

„Checking the work is not the same as doing the work.“

It‘s different. There are people who love coding but don‘t like checking written code. Or the other way around.

Also there’s difference in mental load: checking a finished program or algorithm can be harder than working through it while producing it.

Apart from occasional hallucinations we celebrate their ability to dissect information and to find obscure links between facts. Hence their stunning effectiveness in finding security holes or new approaches to math problems.

Interestingly the generative part - producing the answers - is what we are criticizing a lot: we think the code is verbose, texts have a weird repetitiveness to them etc.

No, it is a guess.

> As opposed to what? This thread is about Linux on Mobile. Are you saying that Linux on Mobile is a lot more efficient than Android?

Opposed to iOS. Android is largely Linux, I think Linux is great and highly performant, just the Android SDK isn‘t.

My gripe with android is that I think it wastes a lot of resources by being very inefficient in software. Just enable the debug mode to see what portion of your screen refreshes and repaints and stand back in awe while nothing changes and you still get hundreds of repaints.

Just no. I developed for android for a long time and I have seldomly seen a worse and more confusing SDK and code base. I can give you many examples but the core layouting algorithm having quadratic complexity with the number of widgets and the single base-view class having 60.000 lines of code are just the tip of the iceberg.

Comments URL: https://news.ycombinator.com/item?id=49155870

Points: 2

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=49146324

Points: 2

# Comments: 0

I wonder whether we are entering the era of throwaway software. Just like cheap plastics and improved processes has enabled us to rapidly manufacture anything we want for a very low price, maybe LLMs give us the same for software. Produce it cheaply and if it breaks throws it away and reproduce it.

Comments URL: https://news.ycombinator.com/item?id=48743437

Points: 6

# Comments: 0

But they pay off by keeping society clean and healthy and prevent loss of workforce from mental or physical disease?

This is an interesting topic. We treat vetting output the same as doing the work ourselves, but that is not the case.

Doing the work is not the same as reviewing work done by others.

I have heard reports of software engineering companies that have gone full agentic. Their seniors only review stuff written by LLMs and it burns them out, because they have to switch context constantly.

I find this interesting because part of being a senior developer is that you are experienced enough that you won‘t make grave mistakes anymore. This is the case in many professions: you are relied upon to not make grave mistakes.

But those same people are now swamped with stuff that they are not able to review, so they will let a grave mistake slip through at some point.

So they really can‘t trust themselves anymore?

What if „being effective at something with pattern matching but not understanding it“ just means that you have identified only 90% of patterns and keep failing to learn the rest for whatever reason.

> „But pattern‑matching is not system understanding, and plausibility is not correctness.“

Why not? Who says that? Who proved that system understanding is not just more complex pattern matching?

> „LLMs predict tokens, not consequences“

Same here. LLMs output tokens but who says that they don’t form some internal group of token-predicting tensors that move together and constitute the internal model of a „consequence“? It is like saying humans don’t have thoughts, they just have electrical impulses moving their tongues.

I too think that LLMs seem to be a very specific form of intelligence, maybe resembling the parts of our brain that do language-processing, but it is a fact that they at least fake intelligence very convincingly. And that we actually don’t know how they do it.

Comments URL: https://news.ycombinator.com/item?id=48065656

Points: 2

# Comments: 0