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

711–720 of 958 posts

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

#711

Post by user34283 »

djhn wrote: post #708
user34283 wrote: post #683

Earlier quoted context omitted.

I would be impressed if you implement it in an hour with the following features: - webview fallback with canvas capture for codecs not supported in the default player - detecting blank frames and diff between thumbnails to maximize variety - UI integration to visualize progress and pending thumbnails, batched updates to the gallery - versioning scheme and backfill for missing/outdated thumbnail formats Honestly, a da…

Ok, fair. I incorrectly assumed you meant resizing static images to create a lower resolution preview image. Video thumbnails are a different beast altogether. And you might want to double check your assumptions about security considerations. If any of your ffmpeg, opencv, pyscenedetect code is running on your server, it might well be exploitable.

It’s in-app on iOS.

Ironically, already another user in this comment section was concerned about the security of my nonexistent backend.

But it’s good to know, I was not previously aware that video processing on the backend is a common source of vulnerabilities.

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

#712

Post by stingraycharles »

timschmidt wrote: post #566
gspr wrote: post #560

Earlier quoted context omitted.

This is actually my biggest gripe with vibecoding. The single best feature of any programming language is that it is precise. And that is what we throw out?! I favor of natural language , of all things?! We're insane!

It turns out an awful lot of precision (plenty for many things) lives in library and web APIs, documentation, header files and dependency manifests. Language can literally just point at it without repeating it all. Avoidance of mistake through elimination of manual copying in things like actuarial and ballistics tables was what the original computers were built for.

Custom written code can also point at those APIs and libraries without repeating it all? Or am I missing your point?

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

#713

Post by AStrangeMorrow »

latexr wrote: post #707
u8 wrote: post #440

The disconnect for AI is that it is a jagged frontier and it only really shines when one of its jagged frontiers extends counter to one of your valleys. If you've been writing Perl for 30 years, you might not want to learn JavaScript just to make a little fun idea in your head to show your wife. Vibe code that shit man. Who cares? Your wife does not care about LOC or those internal design decisions you made. If you'r…

> 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…

I still love learning, especially outside of tech. Been working in the ML field for over 8 years, and while I went into it because I liked the field, I did lose some interest in learning things, but mostly because of the sheer volume of publication and the rate of change. Learning stopped being something I enjoyed doing and went to something I had to do to keep up. And it just stopped having the same flavor.

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

#714

Post by jwpapi »

weird-eye-issue wrote: post #709
jwpapi wrote: post #598

Earlier quoted context omitted.

Average speaking speed for english speakers is 100-120 wpm for complex topic. I type 130wpm peak and I have the most common coding characters on my home row using neo layout.

I hope you never get RSI. It absolutely blows and I can barely type for the last few years without getting pain. And this is with physical therapy...

I had Ulnar Nerve issue, but I’ve changed my setup and it really helped. I don’t have any problems anymore.

It took quite some time to figure out what works and what triggers it. However I don’t know it’s the same for RSI.

I’m grateful for the ability to use speaking as a second option, but utilizing both I can’t cope that speaking is even remotely close to typing :/

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

#715

Post by redsocksfan45 »

gspr wrote: post #560
bulbar wrote: post #531

Earlier quoted context omitted.

Giving a precise description of what the computer is supposed to do is exactly what programming is. The more specific your requirements the closer you get to natural language not being useful anymore.

This is actually my biggest gripe with vibecoding. The single best feature of any programming language is that it is precise. And that is what we throw out?! I favor of natural language , of all things?! We're insane!

[dead]

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

#717

Post by andai »

teddyh wrote: post #360
andai wrote: post #333

Earlier quoted context omitted.

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.)

You mean this one: https://knowyourmeme.com/photos/1567852-shen-comix >

My favorite one:

https://iili.io/BZbHyP9.jpg

I've optimized my game's code and it finally runs at 1000 FPS.

--So your game is good now?

It's shit faster.

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

#718

Post by cpursley »

tdeck wrote: post #568
larodi wrote: post #565

Earlier quoted context omitted.

Care to explain which particular intimate knowledge allowed you in the last 6-9 months to be faster than AI in certain area? Honestly, I'm still faster than AI cooking scrambled eggs, but definitely not faster than neither AI (or compiler) in translating stuff into code.

Not the parent but I've had this happen when debugging for sure. Sometimes I ask Claude Code to help me debug something and it makes a wrong assumption and just churns in circles burning tokens. While it's doing that I realize the problem and fix it.

[dead]

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

#719

Post by andai »

sanderjd wrote: post #337
andai wrote: post #333

Earlier quoted context omitted.

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.

Turns out what was being rewarded all along is "the code looks all right" and "it looks like it works".

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

#720

Post by cpursley »

stephenr wrote: post #621
allthetime wrote: post #490

Earlier quoted context omitted.

AI is just revealing the two types of people in this line of work. Those who don’t actually like software and just do it because it’s lucrative, and the actual nerds who care.

I've posited for a while now that the people who find spicy autocomplete to be exciting are the people who can't really do what it does. I played with Image Playground last year some time. It was really fun. You know why? I can't draw, and I can't paint, to save my life. It's letting me do something I can't do well/at all on my own. Using an LLM to do something I can do, with the caveat that it's pretty mediocre at t…

While you are dying on a hill, with the help of LLMs, I'm shipping quality software and features to my customers at a pace I haven't been able to before. And no, not some nextjs slop. If you are letting your LLM look at StackOverflow, you are doing it wrong - it needs to be grounding in your stacks official docs and any other style/rules you prefer wired with other tooling like linting/formatting, duplication checking, etc. And yes, you have to constantly monitor the output and review every line of code - but it's still faster and if managed correctly, produces better code and (this is the hill I will die on) better test suites and documentation than I would have written.
Post reply on HN