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

331–340 of 958 posts

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

#331

Post by jaggederest »

callc wrote: post #247
Daishiman wrote: post #164

Earlier quoted context omitted.

There's two sides to the AI mandates. The degenerate side is clueless upper management and fad-driven engineering. We have talked extensively about this. There is a more rational side to it that I've seen in my org: some engineers absolutely refuse to use AI and as a consequence they are now, clearly and objectively, much less productive than other engineers. The thing is, you still need to learn how to use the tool,…

Ah yes, we must force these obstinate engineers to the right path! Only after getting everyone to see the light will they understand and thank us for boundless productivity!! /s Perhaps these “obstinate” engineers have good reason in their decision. And it should be their decision! To be so confident in what is “the right way (TM)” and try to force it onto others is... revealing.

Around the turn of the century there were the same exact arguments being made about automated testing (not just TDD, but any automated tests at all!)

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

#332

Post by mleo »

bitexploder wrote: post #120
etothet wrote: post #33

Vibe Coding (and LLMs) did not create undisciplined engineering organizations or engineers. They exposed and accelerated them. Plenty of engineers have loose (or no!) standards and practices over how they write coee. Similarly, plenty of engineering teams have weak and loose standards over how code gets pushed to production. This concept isn't new, it's just a lot easier for individuals and teams who have never reall…

Vibe coded apps with barely no tests, invariants, etc. No wonder it turns into spaghetti. You can always refactor code, force agents to write small modular pieces and files. Good engineering is good engineering whether an agent or human wrote the code. Take time to force agents to refactor, explore choices. Humans must at least understand and drive architecture at this point still. Agents can help and do recon amazin…

I can’t understand this. The first thing I do with new agent driven project is set up quality checks. Linters, test frameworks, static analysis, etc… Whatever I would expect a developer to do, I would expect an agent to do. All implementation has to go through build success and mixed agent reviews before moving on. I might not do this with initial research/throwaway prototype, but once I know what direction to go and expect code to go to production it is vital to set guard rails.

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

#333

Post by andai »

truncate wrote: post #309
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. I don't know if good engineers can necessarily continue to be good. There is limit to how much careful consideration one can give if everything is on an accelerated timeline. Regardless good or not, there is limit on how much influence you have on setting those timelines. The whole playing field is changing.

An old comic I like:

- I've taken a controversial new pill that accelerates my brain.

-- So you're smart now?

- I'm stupid faster!

That being said, being stupid faster can work if validation is cheap (and exists in the first place).

Turns out "eh close enough" for AGI is just stupidity in an "until done" loop. (Technically referred to as Ralphing.)

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

#334

Post by christophilus »

dev360 wrote: post #250

> It’s not just the downstream stuff, it’s the upstream stuff as well. I saw a great talk by Jenny Wen, who’s the design leader at Anthropic, where she said we have all of these design processes that are based around the idea that you need to get the design right—because if you hand it off to the engineers and they spend three months building the wrong thing, that’s catastrophic. This is spot on. I think the tooling…

If you hand something off to engineering and they spend three months building the wrong thing, you’ve got a dysfunctional organization.

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

#335

Post by giulianob »

gverrilla wrote: post #281

> 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. > Claude Code does not have a professional reputation! how come?

That's a wild statement to me. Even with spending significant time making plans with Opus 4.7 and GPT 5.5 on xhigh, I still find lots of poor decisions made when it actually goes to implement it. I find the quality of PRs hasn't dramatically changed either way because the better engineers will spot the issues whereas others will find what the AI is doing acceptable.

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

#336

Post by sanderjd »

truncate wrote: post #309
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. I don't know if good engineers can necessarily continue to be good. There is limit to how much careful consideration one can give if everything is on an accelerated timeline. Regardless good or not, there is limit on how much influence you have on setting those timelines. The whole playing field is changing.

Hmmm, I think I disagree with this.

I estimate that I'm now spending about 10 to 30 hours less time a week in the mechanical parts of writing and refactoring code, researching how to plumb components together, and doing "figure out how to do unfamiliar thing" research.

All of those hours are time that can now be spent doing "careful consideration" (or just being with my family or at the gym or reading a book, which is all cognitively valuable as well).

Now, I suppose I agree that if timelines accelerate ahead of that amount of regained time, then I'm net worse off, but that's not the current situation at the moment, in my experience.

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

#337

Post by sanderjd »

andai wrote: post #333
truncate wrote: post #309

Earlier quoted context omitted.

>> Bad engineers continue being bad, good engineers continue being good. I don't know if good engineers can necessarily continue to be good. There is limit to how much careful consideration one can give if everything is on an accelerated timeline. Regardless good or not, there is limit on how much influence you have on setting those timelines. The whole playing field is changing.

An old comic I like: - I've taken a controversial new pill that accelerates my brain. -- So you're smart now? - I'm stupid faster! That being said, being stupid faster can work if validation is cheap (and exists in the first place). Turns out "eh close enough" for AGI is just stupidity in an "until done" loop. (Technically referred to as Ralphing.)

Yep, validation is key. The smartest thing I've heard on this, which has reoriented how I think about this is that the objective function of a piece of software is now more important to get right than the implementation.

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

#338

Post by solomonb »

From the podcast episode they talk about the idea of using an LLM for training by disallowing the model to write code. I've been experimenting with exactly that in conjunction with a proof checker (Agda) to help me learn some cubical type theory and category theory.

I find the LLM as interactive tutor reviewing my work in a proof checker to be a really killer combo.

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

#339

Post by teeray »

etothet wrote: post #33

Vibe Coding (and LLMs) did not create undisciplined engineering organizations or engineers. They exposed and accelerated them. Plenty of engineers have loose (or no!) standards and practices over how they write coee. Similarly, plenty of engineering teams have weak and loose standards over how code gets pushed to production. This concept isn't new, it's just a lot easier for individuals and teams who have never reall…

Can’t wait for the next stage of escalation when teams start to feel code review is keeping them from vibe coding utopia. It’ll probably be “AI review only, keep your human opinions to yourself” just so they can continue to check the “all changes are reviewed” box on security checklists.

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

#340

Post by user34283 »

jaggederest wrote: post #292
user34283 wrote: post #263

Earlier quoted context omitted.

On the other hand, I don’t need to review carefully every line of code in my thumbnail generator and associated UI. My nonexistent backend isn’t going to be pwned if there is a bug in the thumbnail generation. After the QA testing on my device, a quick scroll through of the code is enough. Maybe prompt „are errors during thumbnail generation caught to prevent app crashes?“ if we‘re feeling extra cautious today. And j…

> My nonexistent backend isn’t going to be pwned if there is a bug in the thumbnail generation. Hmm. Historically image editing was one of the easier to exploit security holes in many systems. How do you feel about having unknown entities having shell inside your datacenter or vpc?

I feel pretty good about the odds of attackers exploiting security holes in image editing functions my app does not have, in order to enter my also nonexistent datacenter or vpc.
Post reply on HN