Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Thoughts on slowing the fuck down

mariozechner.at

Post reply on HN
Print view View original

411–420 of 505 posts

Re: Thoughts on slowing the fuck down

#411

Post by slhck »

chr15m wrote: post #379
emmitska wrote: post #372

"Do me a SOLID, YAGNI, give me a DRY KISS" — that's been my coding philosophy for 20 years. So when I came back to building after a long detour, I couldn't stomach watching agents confidently generate 400 lines where 40 would do. What I found is that the discipline was the feature, not the obstacle. I ended up pair programming closely — not because I distrusted the agent, but because I couldn't let go of the architec…

As well as pair programming with the AI, you can explicitly put those principles in AGENTS.md and the stochastic code generator will pay attention and be less verbose.

Except that when its system prompt is full of instructions, caveats, design principles, gotchas, architecture notes, memories from the past, and personal preferences, at some point it's going to just ignore them outright. Heck, Claude Code won't even use critical instructions from a 100-line CLAUDE.md file sometimes. So you still have to be extremely vigilant about noncompliance.

Re: Thoughts on slowing the fuck down

#412

Post by jimbokun »

HeWhoLurksLate wrote: post #348
jimbokun wrote: post #340

Earlier quoted context omitted.

Sure but maybe we’re all better off spending more time going for walks, learning to cook, playing sports , talking to friends and family, participating in spiritual communities, and making love (to other people !)

This line of reasoning applies to nearly any way to spend time - "why are you playing videogames? Learn X instead!" or "why are you bothering with X when Y exists?" or "what, you don't know how to make sourdough? Silly goose!" At the end of the day, we all have only finite time on this earth, and how one chooses to spend the meager time between eat, sleep, and fend for self is up to them. If a person is content to pl…

Sure but today many of us are spending huge amounts of time every day staring at screens and the evidence suggests it’s damaging our mental health.

Creation on screens is better than mere consumption, but probably still not as good as having less screen time in our days.

Re: Thoughts on slowing the fuck down

#413

Post by puttycat »

> Companies claiming 100% of their product's code is now written by AI consistently put out the worst garbage you can imagine. Not pointing fingers, but memory leaks in the gigabytes, UI glitches, broken-ass features, crashes.

Spotify's CEO recently bragged about the app's code being written almost entirely by AI. Just saying.

Re: Thoughts on slowing the fuck down

#414

Post by pm90 »

tau5210 wrote: post #346
youknownothing wrote: post #311

I understand your pain, we're just a peak hype, I think people will learn to backtrack and use the tool in a more sensible way. It always happens. I remember when MongoDB and other NoSql databases came out, people went as far as to say that "SQL is dead" and refuse to use a normal SQL database for anything. Not even for the most obvious relational application. People would store everything as key-value pairs with no…

Also reminded me of Kafka (Kafka as a database!) and microservices (monoliths are evil, microservices are the future). I'm sure we can dig up similar hypes on various scales throughout the history of this industry... Perhaps so-called AI is slightly different from hypes like NoSql and microservices in that these reduced to usages that practically apply to only a fraction of the engineering population (albeit, it's st…

Technology moves fast and is prone to hype. While NoSQL and Kafka were certainly oversold, almost every mid-large scale tech company has at least one nosql system and kafka-like system in use. The proponents weren’t wrong, they oversold the impact.

There is other tech that did completely change how we do things. CI/CD, Containers, Kubernetes, distributed tracing etc. are considered standard now (but weren’t not that long ago).

Re: Thoughts on slowing the fuck down

#416

Post by postexitus »

MrScruff wrote: post #257
postexitus wrote: post #82

Earlier quoted context omitted.

You sound like you are working on unimportant stuff. Sure, go ahead, push.

Honestly a lot of useful software is ‘unimportant’ in the sense that the consequences of introducing a bug or bad code smell aren’t that significant, and can be addressed if needed. It might well be for many projects the time saved not reviewing is worth dealing with bugs that escape testing. Also, it’s entirely possible for software to be both well engineered and useless.

Exactly - not so much in "important" stuff.

Re: Thoughts on slowing the fuck down

#417

Post by drzaiusx11 »

The article touches on this but I think the key takeaway is that humans need to properly manage the _scope of work_ for their agentic teams in order to have any chance of a successful outcome.

Current gen agents need to be provided with small, actionable units of work that can _easily_ be reviewed by a human. A code deliverable is made easy to review if the scope of change is small and aligned with a specific feature or task, not sprawled across multiple concerns. The changes must be ONLY related to the task at hand. If a PR is generated that does two very different things like fix linting errors in preexisting code AND implement feature X, you're doing it wrong. Or rather, you're simply gambling. I'd rather not leave things up to chance that I may miss something in that new 10000LOC PR. It's better that a 10000LOC never existed at all.

YOLOing out massive, sweeping changes with agents exceed our own (human) "context windows" and as this article points out, we're then left with an inevitable "mess." The untangling of which will take an inordinate amount of time to fix.

Re: Thoughts on slowing the fuck down

#418

Post by shmel »

Towaway69 wrote: post #124

What the article doesn't touch on is the vendor lock-in that is currently underway. Many corps are now moving to an AI-based development process that is reliant on the big AI providers. Once the codebase has become fully agentic, i.e., only agents fundamentally understand it and can modify it, the prices will start rising. After all, these loss making AI companies will eventually need to recoup on their investments.…

I think it will be more similar to the cloud. I remember people predicted that once you move to the cloud, you'll realize how expensive it actually is, but the cost of migration back will be high. While, yes, the cloud is expensive, most people realized that it is kinda worth it.

Re: Thoughts on slowing the fuck down

#419

Post by sigbottle »

roughly wrote: post #162
bigstrat2003 wrote: post #156

Earlier quoted context omitted.

If you were going to dismiss an argument because of who it comes from rather than its content, that is a flaw in your thinking. The argument is correct, or it isn't, no matter who said it.

Your ability to evaluate whether the argument is correct is limited. In theory, the author and the correctness of the argument are unrelated; in practice, the degree of experience the author has with the topic they’re making an argument on does indeed have some correlation with the argument and should influence the attention you give to arguments, especially counterintuitive ones.

Even further, not everything is a math proof, where everything has been standardized and open (although understanding the proof is a whole other topic). Heck, take it one step lower - coding - and even though theoretically the source code is 100% transparent, still often times your claims are not reproducible because of environment. Now lower it one more to any kind of science where replication is expensive and/or hard, and then one step lower to personal experiences... And yeah, things can seem tough, can't it?

And even in the case of mathematics proofs, that tells you nothing about things such as: extendability, taste, where future direction should go, what this philosophically means, etc. Which we definitely do care about.

It's funny because the people throwing around fallacy accusations everywhere don't understand that they are semi selectively using fallacies alongside claiming universality while not actually practicing it (not that you have to, of course, I very much don't agree with that premise, but if you're the one saying it...)

Anyways. /rant, it's crazy how many people don't discuss these basic but subtle ideas. To be fair, I struggled with the same exact things when I was 15, and it doesn't seem like you get taught this kind of nuance until maybe the tail end of a rigorous bachelor's degree, though personally I only learned this stuff on my own through extensive trial and error and suffering.

Re: Thoughts on slowing the fuck down

#420

Post by mojosam »

Towaway69 wrote: post #124

What the article doesn't touch on is the vendor lock-in that is currently underway. Many corps are now moving to an AI-based development process that is reliant on the big AI providers. Once the codebase has become fully agentic, i.e., only agents fundamentally understand it and can modify it, the prices will start rising. After all, these loss making AI companies will eventually need to recoup on their investments.…

> Once the codebase has become fully agentic, i.e., only agents fundamentally understand it

What exactly do we mean this? Because it is obviously common for human coders to tackle learning how an unfamiliar and complex codebase works so that they can modify it (new hires do it all the time). I can think this means one of two things:

* The code and architecture being produced by agents takes approaches that are abnormally complex or inscrutable to human reviewers. Is that what folks working with cutting edge agents are seeing? In which case, such code obviously isn’t beeping reviewed; it can’t be.

* the code and architecture being produced by agents can still be understood by human reviewers, but it isn’t actually being reviewed by anyone — since reviewing pull requests isn’t always fun or easy, and injecting in-depth human review slows everything down a lot — and so no one understands how the code works. (I keep thinking about the AI maximalist who recently said he woke up to 75 pull requests from his agent, like that was a good thing)

And maybe it’s a combination of the two: agent-generated pull requests are incrementally harder to grok, which makes reviewing more painful and take longer, which means more of them go without in-depth reviews.

But if your claim is true, the bottom line is that it means no one is fully reviewing code produced by agents.

Post reply on HN