In my own experience, good engineering practices are still not easy to achieve. As a software engineer with three years of experience, I've been doing solo dev for the past few months. Currently, there is still a lot of the harness to set up manually.
Vibe coding and agentic engineering are getting closer than I'd like
701–710 of 958 posts
Re: Vibe coding and agentic engineering are getting closer than I'd like
#702Reminder, cybersecurity will be huge in following years.
Companies are shipping things and nobody understands what they're shipping.
Re: Vibe coding and agentic engineering are getting closer than I'd like
#703[dead]
Re: Vibe coding and agentic engineering are getting closer than I'd like
#704Earlier quoted context omitted.
I agree with you on everything you said here except: > when you know how the thing works and have that mental context, you will always be faster than an AI That's just plain false, honestly. No one can type at the speed AI can code, even factoring in the time you need to spend to properly write out the spec & design rules the AI needs to follow when implementing your app/feature/whatever. And that gap will only incre…
Some of us do actually have intimate knowledge in certain areas where guidance of an AI takes longer than doing it yourself. It's not about typing speed, it's that when you know something really really well the solution/code is already known to you or the very act of thinking about the problem makes the solution known to you in full. When that happens it's less text to write that solution than it is to write a suffic…
That doesn't matter. The statement wasn't "faster than AI right now", it was "will always be faster than AI". And that's just nonsense.
Current AI systems are extremely serial, in that very little of the inherent parallelism of the problem is utilized. Current-gen AI systems run at most a few hundreds of thousands of operations in parallel, while for frontier models, billions of operations could be run in parallel. Or in other words, what currently takes AI 8 hours will take it barely long enough for you to perceive the delay after you release the enter key.
For a demo, play around with https://chatjimmy.ai/ , the AI chatbot of Taalas, where they etched the model into silicon in a distributed way, instead of saving it in RAM and sucking it to execution units by a straw. It's a 8B parameter model, so it's unsuitable for complex problems, but the techniques used for it will work for larger models too, and they are working to get there.
And even Taalas is very far from the limits. Modern better quality LLM chatbots operate at ~40 tokens per second. The Taalas chatbot operates at 17000 tokens/s. If you took full advantage of parallelism, you should be able to have a latency of low hundreds of clock cycles per token, or single request throughput of tens of millions of tokens per second. (With a fully pipelined model able to serve one token per clock cycle, from low hundreds of requests.) Why doesn't everyone do it like that right now? Because to do this, you need to etch your model into silicon, which on modern leading edge manufacturing is a very involved process that costs hundreds of millions+ in development and mask costs (we are not talking about single chips here, you can barely fit that 8B model into one), and will take around a year. So long as the models keep improving so much that a year-old model is considered too old to pay back the capital costs, the investment is not justified. But when it will be done, it will not just make AI faster, it will also make it much more energy-efficient per token. Most of the energy costs are caused by moving data around and loading/storing it in memory.
And I want to stress that none of the above is dependent on any kind of new developments or inventions. We know how to do it, it's held back only by the pace of model improvement and economics. When models reach a state of truly "good enough", it will happen. It feels perverse to me that people are treating this situation as "there was a per-AI period that worked like X, now we are in a post-AI period and we have figured out that it will work like Y". No. We are at the very bottom of a very steep curve, and everything will be very different when it's over.
Re: Vibe coding and agentic engineering are getting closer than I'd like
#705[dead]
Re: Vibe coding and agentic engineering are getting closer than I'd like
#706Earlier quoted context omitted.
>you’re not great at writing prompts yet How do you reconcile that with your example prompt, which demonstrates no skill requirement whatsoever. It’s the first thing any developer would think of.
It’s simple but contains all the necessary info. You can say “build an endpoint to get user data” and it will absolutely do something, but it might be stupid, and when you compound 1000 stupid prompts like that you get spaghetti.
It doesn’t contain any information at all about the structure of the JSON output. Is this a greenfield endpoint and anything will work is does it need to conform to an existing API? What about response codes for different failure modes? What about logging?
Your comment exemplifies what a lot of people complain about vibe coding: it works great for greenfielding CRUD apps, but it’s a bitch to use in a real code base.
Re: Vibe coding and agentic engineering are getting closer than I'd like
#707The 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 otherwise go. Curiosity kicks in. Curiosity is a precursor to learning. Learning engages the brain and is fun. But it’s not fun all the time, some of it is challenging and frustrating (which is good, that’s the process that teaches you).
When you have the digital equivalent to infinite candy and the brain equivalent to a sweet tooth, it’s hard to resist the siren’s call. The consequence is the brain equivalent to a stomachache—depression and loss of meaning—but unfortunately it doesn’t hit you the same way so you don’t make the immediate connection to make yourself stop. When you think about it, it’s ridiculous from several angles: the candy is infinite, it’s never going to run out, so you don’t need to gorge! But then we justify ourselves as only a true addict would, that while the candy is infinite, the flavours are limited editions and always rotating, and what if I miss that really good one everyone is on?! Then you miss it, is the answer. No one will be talking about it in fifteen minutes anyway.
Re: Vibe coding and agentic engineering are getting closer than I'd like
#708Earlier quoted context omitted.
But a thumbnail generator is a 1 hour task at best if you’re on a solo greenfield project and it’ll still be a 6 week project at an enterprise, even with AI.
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.
Re: Vibe coding and agentic engineering are getting closer than I'd like
#709Earlier quoted context omitted.
You're still typing? I don't know how fast you can type, but I can speak way faster than I can type. Somewhere in the neighborhood of 300 wpm. Speech-to-text is pretty good now, and prompting an AI means I'm not trying to speak curly brace semicolon new line.
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...
Re: Vibe coding and agentic engineering are getting closer than I'd like
#710Earlier quoted context omitted.
The exceptions that prove the rule. When your programming language is built up of singular Unicode characters with specific meanings, of course that's faster than typing out in English what you want. What do you use them for? For most AI users it's usually CRUD and I've never seen a web server or frontend in APL like languages.
The exception is the rule. The reason why programming is hard is because most languages force you to use a hammer when you need a screw driver. LLMs are very good at misusing hammers and most people find them useful for that reason. If you use a sane dsl instead the natural language description of a problem is always more complex and much longer than the equivalent description in a dsl. It's also usually wrong to boo…
Using esoteric programming languages doesn’t suddenly make it true for the majority of development, which is web apps, CRUD stuff, some data science, etc.