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

881–890 of 958 posts

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

#881

Post by theshrike79 »

skydhash wrote: post #796
theshrike79 wrote: post #778

Earlier quoted context omitted.

API Glue is the easy and boring part in programming. Nobody really enjoys wiring API A to API B, combining the results and using API C to push it forwards. Any semi-competent AI Agent can do that with a plan you've written in 5 minutes.

I would love to see an AI try to make sense of GTK API. I may be wrong, but it seems when people are talking about easy glue code, they’re talking about web services API, not OS API, not graphics or sound API, not file formats libraries,…

I used Sonnet 3.5 over a year ago to decrypt a notoriously shitty local government API to get data out of meetings, votes and discussions.

I know it's a piece of shit API done in the worst possible way on purpose (they don't want openness, but had to fulfill a law that mandates "openness") because I had previously tried to do it manually - twice. I ran out of whisky before I got anything done.

Sonnet _3.5_ almost one-shotted it with just the API "documentation" they had and access to Python and curl.

People have also hooked stuff into proprietary APIs on "smart" devices with zero documentation, just by having an Agent tirelessly run through thousands of permutations to figure it out.

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

#882

Post by gchamonlive »

fugalfervor wrote: post #877
gchamonlive wrote: post #811

Earlier quoted context omitted.

we can also apply regulations but they are also not enough, otherwise people wouldn't OD on controlled substances. At one point the individual needs to start taking responsibility for their actions.

And the unscrupulous purveyors of addictive products should likewise take responsibility for their actions. How often do you see that happen, though?

Not nearly enough, this is why as an individual we need to be twice as vigilant

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

#883

Post by theshrike79 »

swsieber wrote: post #792
latexr wrote: post #782

Earlier quoted context omitted.

I don’t see what that has to do with “when did we stop liking to learn”, which is the only point I’m addressing. My point has nothing to do with AI and it doesn’t seem like you actually learned anything from that experiment.

I read it more as response to your argument that it was a lack of curiosity due to over stimulation, which they responded to by citing an example of a time when they were curious while stimulated and chucked something at a vibe-coding agent to satisfy that curiosity.

Yep, now I have the time to satisfy my curiosity in weird things because it doesn't take active time from me that much.

Before all those curiosity brain farts would've just slipped away with "oh well, I'll never have the time to find out".

Wikipedia has scratched the same itch multiple times, but from a different angle. Doing deep dives in weird stuff is so much easier with Wikipedia than it used to be when you had to go to the library and pull books from the shelves for an hour or two.

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

#884

Post by fugalfervor »

gchamonlive wrote: post #804
latexr wrote: post #780

Earlier quoted context omitted.

> gambling sites, in alcohol, tobacco and highly processed foods, or in the scamming industry Those are great examples because they show that leaving it all up to the individual is not enough. All of those are regulated by the state because we as a society recognised they were doing their damnest to screw everyone else for their own gain. Social media is going the same route, with several countries already introducin…

Exactly, but I still think those are two slightly different conversations. If we are talking about harmful habits at a more general level, I'll defend that we need to be very restrictive in those examples. Online gambling, alcohol use and such shouldn't be allowed to advertise, it should pay almost prohibitively expensive taxes etc... But if we are talking about the individual, the one inserted in the society, which…

You've clearly never been addicted to anything. You seem to have little understanding of, or empathy for, those who have become addicted.

I quit smoking cigarettes. It took years. It was incredibly difficult on an emotional level, and took a lot of failure and disappointment to finally make it through. And I almost lost all my progress when I relapsed after my Dad died unexpectedly.

Every pair of eyes that you see walking down the street has an entire universe behind them that we cannot see. It is not simple like you assume.

I suggest you recognize your exceptional self-discipline and relatively unaddicted lifestyle as the stroke of good fortune that it is; you are genetically predisposed or developmentally more well-prepared than most. Recognize that others are less fortunate than you in that regard, but no less deserving of aid, comfort, and a legal avenue to seek recompense from unscrupulous actors.

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

#885

Post by _DeadFred_ »

gchamonlive wrote: post #732
latexr wrote: post #707

Earlier quoted context omitted.

> Also, when did we stop liking to learn? I suspect it happened when we achieved a level of such constant stimulation (there is a pocket computer always on us with infinite effortless distraction) that we’re never bored and never engage the default mode network. https://en.wikipedia.org/wiki/Default_mode_network https://www.youtube.com/watch?v=orQKfIXMiA8 When you’re bored, your mind goes to places it wouldn’t otherw…

> it happened when we achieved a level of such constant stimulation (...) that we’re never bored and never engage the default mode network. I don't know... I don't disagree, but I think this has been repeated so much that I believe everyone, at least everyone that is actively participating in HN discussions is aware of this. So if we are aware of this and we consciously choose to keep engaging in dopaminergic activit…

You are pitting your randomly acquired will power and your in large part unintentional stumbling through life against all of human kind's psychology knowledge, against billions of dollars spent on advertising and advertising research. That is at this point tens maybe hundreds of millions of years of acquired human knowledge how to manipulate you versus your very randomly acquired 'will power'.

Have you seen the quotes coming out of the richest/most powerful companies on the planet? These are very intentional impacts by companies more powerful than entire nations.

I don't think 'but your willpower' stands a chance if you want to be connected to the modern world.

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

#887

Post by randallsquared »

kiba wrote: post #784
therealpygon wrote: post #757

Earlier quoted context omitted.

Or at least, aware that this argument continues to be made with tenuous evidence and anecdotes. And yet, people are being more productive (actually productive) with AI. Release schedules are increasing, bugs are getting fixed faster, security issues identified and patched sooner, so on and so forth. I’m not denying (at all) that unused skills languish. I take issue with AI being characterized as a magic eraser that m…

Can AI make developers lazy in new ways? Of course! Why wouldn’t it? I don’t write things in ASM because I can be “lazy” and write 50x more useful instructions with a few lines of a modern language. I doubt I’d be able to write working ASM anymore without a serious refresher. Did newer languages erase my memory of ASM and make me “lazy”, or did my efforts evolve to make use of the newest technology regardless of “los…

> If the point of an engineer is to know how things work behind a piece of software

That might be the point of an engineer in some orgs, but mostly the point of an engineer is to ship a product or release that matches someone's vision of what should come next, and doesn't cause additional noticeable problems in the next quarter or three.

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

#888

Post by esafak »

hnuser123456 wrote: post #399
jwpapi wrote: post #398

Earlier quoted context omitted.

I don’t want every verb implemented, I also dont want an IETF standard. I want as little as possible, so I have to worry about as little as possible in the future. Use-cases differ, you described a complete REST API, which can be as much of a problem as a too little.

I see you haven't encountered an API where a GET command can modify the database.

I saw a code base where SQL UDFs were used to mutate the data with SELECTs...

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

#889

Post by awalGarg »

eddieroger wrote: post #416
jwpapi wrote: post #373

> I know full well that if you ask Claude Code to build a JSON API endpoint that runs a SQL query and outputs the results as JSON, it’s just going to do it right. It’s not going to mess that up. You have it add automated tests, you have it add documentation, you know it’s going to be good. I feel like this is just not true. An JSON API endpoint also needs several decisions made. - How should the endpoint be named - W…

> If I know the answer to all these questions, wiring it together takes me LESS time than passing it to Claude Code. That's just not true, and if it is in your case, then you're not great at writing prompts yet. > Take the todo_items table in Postgres and build a Micronaut API based around it. The base URL should be /v1/todo_items. You can connect to Postgres with pguser:pgpass@1.2.3.4 That's about all it takes these…

> > If I know the answer to all these questions, wiring it together takes me LESS time than passing it to Claude Code.

> That's just not true, and if it is in your case, then you're not great at writing prompts yet.

That's just not true, and if it is in your case, then you're not great at writing code yet.

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

#890

Post by esalman »

zarzavat wrote: post #24

Perhaps I've missed a few weeks worth of progress, but I don't think that AIs have become more trustworthy, the errors are just more subtle. If the code doesn't compile, that's easy to spot. If the code compiles but doesn't work, that's still somewhat easy to spot. If the code compiles and works, but it does the wrong thing in some edge case, or has a security vulnerability, or introduces tech debt or dubious archite…

This.

My manager reported couple of days ago that copilot manipulated some tests in order to make edge cases pass.

We have standalone prototypes for our product, so it was easy to catch, but actually going in to debug and fix was much harder than expected.

It absolutely did nothing to increase confidence on copilot though. I personally manually accept each line of code copilot writes, unless it's a skill/mcp server we have no plan to deploy.

Post reply on HN