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

891–900 of 958 posts

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

#891

Post by Daishiman »

anygivnthursday wrote: post #642
Daishiman wrote: post #541

Earlier quoted context omitted.

I am not really sure. I wrote some scripts that aggregated data from several APIs with an LLM and the LLM had the foresight to create a caching layer for the API responses as it properly inferred that I would need the results over and over again as well as using asyncio to accelerate fetch speed. This would have been a v2 or v3 and it one-shotted it perfectly.

Yeah, they are good at applying generic patterns, but often it can be overkill/YAGNI that lead to more maintenance work in places that are fine with a much simpler/straightforward solution. But this is what the engineer can decide and with LLMs they wont be forced to make the trade off because it takes longer to build, but rather whether it is really necessary or not.

For sure, but the engineer will always be ultimately responsible. There's always a QA and review stage in my process for trimming the fat.

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

#892

Post by pydry »

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,…

Even with web services it usually shits the bed if you ask it to maintain something with tech debt.

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

#893

Post by gchamonlive »

fugalfervor wrote: post #884
gchamonlive wrote: post #804

Earlier quoted context omitted.

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 wa…

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 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. Just like it's your merit to quit it, it would have been just as well your fault if you kept on smoking after recognizing you needed to quit.

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

#894

Post by lmeyerov »

mittensc wrote: post #698
lmeyerov wrote: post #588

Earlier quoted context omitted.

That's the failure to automate. The AI isn't telepathic, so agentic engineers not automating this stuff is skipping out on the engineering part. You setup the environment and then you do the work. Unless you are switching employers every week, you invest in writing that stuff down so the generation is right-ish and generate validation tooling so it auto-detects the mistakes and self-repairs.

sometimes you write the feature and write it well so it's reusable. imagine you have to implement a specific algorithm for a quantum computer. There's no value setting up AI to do the writing for you. That might be orders of magnitude harder then writing the algorithm directly. For highly specialized one-off features, it doesn't always pay off. On the other hand, if all you do are some generic items that AI can do we…

That feels like true in theory, but in practice, we see the reverse for advanced projects where AI is helping us a lot. A decent chunk of our core IP falls into the bucket you're describing:

We have been building a GPU-accelerated graph investigation platform that has grown over 10+ years with fancy stuff all over the place - think accelerated query languages, layout kernels, distribution, etc. R&D-grade high performance engineering projects and kernels end up needing a lot of iterations to make a prototype and initial release. Likewise, they're more devilish to maintain when they need a small tweak later because of the sophistication and bus factor. Both phases benefit.

AI coding helps automate investigation, testing, measurement, patching, etc. The immediate effect is we can squeeze in many more experimental iterations with more fidelity and reach. Having an AI help automatically explore the design space and the details helps a LOT. And later, maintaining a wide surface area of code here that is delicate to touch and infrequently edited is traditionally stressful for teammates, and AI editing + AI-generated automation is helping destress that a LOT. We very much invest in upgrading our team, processes, and tooling here.

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

#896

Post by threethirtytwo »

matt_kantor wrote: post #755
threethirtytwo wrote: post #723

Earlier quoted context omitted.

Ok sorry about that. I seriously don't believe him. The Agent is so fast there's literally no way you can be faster. Telling the agent your high level plan that you are extremely familiar with and then having the agent execute on 2000 lines of code is FASTER then having you execute on that 2000 lines of code. There is no reality where that can be physically beaten by even someone who's typing really quickly with zero…

Why are you starting the clock at the time when you already have a "high level plan that you are extremely familiar with"? I think it's fairer to start from "I received a bug report/feature request" or similar. Also, haven't you ever had a situation where the prompt you started with ends up being longer than the final code diff? Perhaps a subtle bug that's hard to describe/trigger, but ended up having a simple root c…

>Why are you starting the clock at the time when you already have a "high level plan that you are extremely familiar with"? I think it's fairer to start from "I received a bug report/feature request" or similar.

Done both. We tag the LLM on slack in a reply and the ticket gets created and forwarded to an agent that automatically works on it. The only time a human is in the loop is review or or queries for changes.

>Also, haven't you ever had a situation where the prompt you started with ends up being longer than the final code diff? Perhaps a subtle bug that's hard to describe/trigger, but ended up having a simple root cause like an off-by-one error?

Sometimes. Getting rarer and rarer.

>Also also, coding agents are infamous for generating way more code than is strictly necessary. The 2000 lines of code that the agent generated may well have been only 200 lines had you written it yourself.

Depends on the agent and it's random. This was mostly true probably 5 months ago. It's much less true now.

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

#897

Post by threethirtytwo »

dzjkb wrote: post #734
threethirtytwo wrote: post #723

Earlier quoted context omitted.

Ok sorry about that. I seriously don't believe him. The Agent is so fast there's literally no way you can be faster. Telling the agent your high level plan that you are extremely familiar with and then having the agent execute on 2000 lines of code is FASTER then having you execute on that 2000 lines of code. There is no reality where that can be physically beaten by even someone who's typing really quickly with zero…

AI can write 2000 lines faster than you, but you can write the 2000 lines correctly first shot faster than having AI do 10 iterations on these 2000 lines with your guidance to finally get it right I know that a better plan could mean fewer iterations, but again that extends the time you need to spend on that plan => the total time of the AI solution

Right but those 10 iterations only take up prompt writing time. When the agent is executing I move onto other tasks in parallel. AI is faster when you parallelize your work flow.

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

#898

Post by threethirtytwo »

notnullorvoid wrote: post #821
threethirtytwo wrote: post #723

Earlier quoted context omitted.

Ok sorry about that. I seriously don't believe him. The Agent is so fast there's literally no way you can be faster. Telling the agent your high level plan that you are extremely familiar with and then having the agent execute on 2000 lines of code is FASTER then having you execute on that 2000 lines of code. There is no reality where that can be physically beaten by even someone who's typing really quickly with zero…

Again it's not about typing speed. High level plans simply don't work very well, especially for big tasks where the optimal solution actually would take 2k lines. Unless you are building something that is extremely generic, AI coming up with the optimal solution rarely ever happens. > He is either a liar or like many other people lacks skill in using AI Not a liar, and I'm sorry to say, but AI really doesn't take muc…

>Again it's not about typing speed. High level plans simply don't work very well, especially for big tasks where the optimal solution actually would take 2k lines. Unless you are building something that is extremely generic, AI coming up with the optimal solution rarely ever happens.

Nope. Not universally true. It depends on randomness of the rng, the type of task, the agent, and also the current state of AI. Right now for frontier models... what you're saying is generally true only in the minority of times ime.

>Not a liar, and I'm sorry to say, but AI really doesn't take much skill to use. People who say such statements give me the impression that their ceiling for skills is quite low.

It does take a little skill. Very little and it requires new habits that are harder to pick up. For example. I never work on one project at a time anymore. I work on 5 projects and context switch between all of them. Prompt, switch, come back, prompt, switch, prompt switch, review... etc. That takes getting used to.

>I make templates I can copy and tweak to do this faster than it takes to tell an agent what to do.

I have a huge change, and within that change the agent does this automatically.

>Don't do that... Sure get it to write you some SQL to update a table, but don't give it DB admin access for fucks sake.

You can fuck off prick, don't fucking talk like that to my face. I do it and I have no problems with it. If you don't want to, that's your own fucking prerogative.

>Tell me, how is your agent able to deploy code more effectively than hitting merge on a PR? Or do you simply mean setting up CI/CD for you? That's usually a set and forget thing that doesn't take much time, so I'd rather do it myself.

Because the agent merges for me. Prompt: "Complete task A". Agent: "Task completed", Me: "reviewed and good to go"

The agent then does it's thing. Of course there's always some adjustments and more conversation then this but that's the jist of it.

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

#899

Post by esafak »

xienze wrote: post #74
wavemode wrote: post #42

Earlier quoted context omitted.

You're comparing paying $20 for an AI plumber to paying hundreds/thousands for a traditional plumber. But that's not what the author is talking about in that passage you quoted. What he's saying is that, if you can pay $20 for an AI plumber, then it stands to reason that eventually you will be able to pay $30 to a company that manages AI plumbers for you, so that you don't even have to go to the trouble of supervisin…

It's in a section called "Why I’m still not afraid for my career." The implication here is software engineer jobs are still safe despite basically free labor/material being available to do said jobs because he thinks other people would prefer to pay experienced professionals to do it right at a significantly higher cost. My point is, I think most people will take the low-stakes gamble of having the cheap AI agent do…

Do humans take a pay cut when they manage other humans? Does directing agents take little technical skill that merits a pay cut?

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

#900

Post by a456463 »

Hot take: most people are shit at writing code or logic. We are just going to see more of this vibe coding. This is exposing the bad coders more than anything else. Everything to do with preventing and stabilizing vibe code is what we had to do on a longer scale, now we have to do it a lot more and faster
Post reply on HN