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

Vibe coding and agentic engineering are getting closer than I'd like

simonwillison.net

Post reply on HN
Print view View original

931–940 of 958 posts

Re: Vibe coding and agentic engineering are getting closer than I'd like

#931

Post by gchamonlive »

latexr wrote: post #929
gchamonlive wrote: post #893

Earlier quoted context omitted.

You might disagree with my point, but you don't know me and you can't really lecture me on empathy. You just glossed over the parts of the argument where I am for discussing public policies that we can implement to care for those that suffer from addiction. But at the individual level, after recognizing the hardships of being addicted to anything, the ultimate choice and responsibility to do something is yours. Your…

> Your cigarette addiction might have started because of social pressure or because of advertisement, but every choice to light another one or not was entirely yours. This is contradictory. Once you are addicted, the choice is no longer “entirely yours”. That’s what being an addict means, your physiology and your wants are in conflict and require constant active vigilance to contradict. Your head begins to rationalis…

I am rereading my comments and you guys are right. What I meant to say and got sidetracked by doubling down on the "your fault" argument is that you can't help someone that doesn't want help. In this sense it's the responsibility of the person that got some kind of addiction to first recognize that they need to want to get help, only then help is effective. But yeah, you are right saying that you are like a different person on a abstinence episode.

Wish I could rephrase my comments, but at least I know next time I will treat this topic with more care.

Re: Vibe coding and agentic engineering are getting closer than I'd like

#932

Post by theshrike79 »

sarchertech wrote: post #903
theshrike79 wrote: post #810

Earlier quoted context omitted.

If it's not a greenfield project, the Agent will go and look at the other endpoints and mimic the style as much as possible. Just like a human would. "But we have documentati..." then give the Agent access to the same docs as humans and it'll use them.

On a real codebase there’s going to be v5 that is the newest version, v4 that we planned to migrate off of but we had to keep around for iOS clients, and v3 that no one except for a dozen huge enterprise customers use. But we need to support all 3 styles. This stuff is sort of documented, but not completely, and there’s a push by some people in the org to use v5 style for every new feature, but there’s one director p…

AI can't fix shit processes =)

I actually believe it just surfaces them, humans will tolerate ambiguity like that and deal with it. AI Agents either won't work properly or will just fail to do anything useful.

Re: Vibe coding and agentic engineering are getting closer than I'd like

#934

Post by latexr »

gchamonlive wrote: post #931
latexr wrote: post #929

Earlier quoted context omitted.

> Your cigarette addiction might have started because of social pressure or because of advertisement, but every choice to light another one or not was entirely yours. This is contradictory. Once you are addicted, the choice is no longer “entirely yours”. That’s what being an addict means, your physiology and your wants are in conflict and require constant active vigilance to contradict. Your head begins to rationalis…

I am rereading my comments and you guys are right. What I meant to say and got sidetracked by doubling down on the "your fault" argument is that you can't help someone that doesn't want help. In this sense it's the responsibility of the person that got some kind of addiction to first recognize that they need to want to get help, only then help is effective. But yeah, you are right saying that you are like a different…

[dead]

Re: Vibe coding and agentic engineering are getting closer than I'd like

#935

Post by yieldcrv »

theteapot wrote: post #426
yieldcrv wrote: post #391

Earlier quoted context omitted.

I’ve seen the best REST APIs since Claude Code has taken the wheel Every verb implemented, and implemented correctly according to the obscure IETF and most compatible way when the IETF never made it clear Intuitively named routes, error, authentication all easily done and swappable for another if necessary I feel like our timeline split if you’re not seeing this

the obscure IETF? Which standard is that exactly? Who cares guess - Claude do that stuff.

I've tried to implement REST to its exact specifications before, turns out less common verbs like DELETE isn't implemented the same way across platforms and libraries because the IETF never specified. This means no standardization regarding having variables in the path vs the body vs headers, with some libraries or even OS level recognition preventing that, while the server may be looking for it

this incongruence pushes people back to using just GET and POST methods in flexible and overloaded ways

Agentic engineering knows all the best practices and ways to get around these limitations in the most compatible way and cranks out full APIs with all the verbs

Re: Vibe coding and agentic engineering are getting closer than I'd like

#936

Post by threethirtytwo »

notnullorvoid wrote: post #535
datsci_est_2015 wrote: post #71

Earlier quoted context omitted.

Bad engineers continue being bad, good engineers continue being good. I personally don’t know any colleagues who were good engineers just because they wrote code faster. The best engineers I know were ones who drew on experience and careful consideration and shared critical insights with their team that steered the direction of the system positively. > Claude, engineer a system for me, but do it good. Thanks!

> Bad engineers continue being bad, good engineers continue being good. Unfortunately I have seen some really good software engineering peers regress into bad engineers through a increasing reliance on AI. Conversely some very bad engineers (undeserving of the title) have been producing better outputs than I ever expected possible of them.

Which one are you?

Re: Vibe coding and agentic engineering are getting closer than I'd like

#937

Post by senordevnyc »

jwpapi wrote: post #905
senordevnyc wrote: post #853

Earlier quoted context omitted.

This is just bizarre to me. Do people not use Plan mode? I start by telling the agent what I'm trying to accomplish, and then I throw in some questions like this, concerns I have, edge cases I've thought about, whatever. It goes out and does all the research, both in my code base and beyond, asks me questions where it needs clarification, and then writes me a plan. I review the plan, we go back and forth a bit with a…

You getting swindled into over-engineering.

Sure, if I don’t do the barest minimum of my job, and tell the agent what I want to do and what I don’t care about.

Re: Vibe coding and agentic engineering are getting closer than I'd like

#938

Post by sarchertech »

theshrike79 wrote: post #932
sarchertech wrote: post #903

Earlier quoted context omitted.

On a real codebase there’s going to be v5 that is the newest version, v4 that we planned to migrate off of but we had to keep around for iOS clients, and v3 that no one except for a dozen huge enterprise customers use. But we need to support all 3 styles. This stuff is sort of documented, but not completely, and there’s a push by some people in the org to use v5 style for every new feature, but there’s one director p…

AI can't fix shit processes =) I actually believe it just surfaces them, humans will tolerate ambiguity like that and deal with it. AI Agents either won't work properly or will just fail to do anything useful.

Every group of humans has shit processes. So if you’re trying to use AI in an actual company, today, that prompt won’t work properly or will just fail to do anything useful.

Re: Vibe coding and agentic engineering are getting closer than I'd like

#940

Post by chickensong »

orphea wrote: post #763
chickensong wrote: post #267

Earlier quoted context omitted.

Yes. The models may have started from indiscriminate scraping, but people are undoubtedly working on refining the training data. Combined with the overall model capabilities, I suspect code quality will continue to go up. What you're suggesting is a negative flywheel where quality spirals down, but I'm hoping it becomes a positive loop and the quality floor goes up. We had plenty of slop before LLMs, and not all LLM…

Let's agree to disagree. What I see is that while LLMs can do real tasks, they often produce overengineered unmaintainable slop (plenty of examples where code can be reduced 10x to do the same). I hope this is not a base to continue training LLMs on.

I don't disagree that there's a lot of slop getting churned out, you're not wrong there. I just have hopes that we'll course-correct after some initial adjustment period, but I have no idea how long that might be (guessing several years).

I don't know how long LLMs will hold their position, but in my mind, it makes sense that computers will eventually be the best programmers. Humans will still guide, but rarely write or even read code. I might be dead by then, but that's my prediction for the future.

Post reply on HN