All of these complaints are about humans making user-hostile decisions, not AI. And software quality is not a reflection of its code quality. Never has been.
> This was just before Claude Code was released so this wasn't full agentic hands-off engineering. Instead, I broke down the development into lots of small tasks and went through them manually with the AI, testing each change as I went along
Is there really much use in deconstructing a vibe coding process that was used before the term "vibe coding" existed? It's like critiquing a caveman's fire-starting routine.
> Meanwhile, the senior developers are in 2 camps. One half are using AI for absolutely everything but are slowly losing their ability to code. The other half are so sick of AI and are getting burnt out having to write prompts every day that they just don't want to do it anymore.
Again, this sounds like what developers were saying about AI a year ago. The refrain from the development world hasn't sounded like that for a while.
The most important prompt lesson everyone should take away: never ask yes / no / leading questions.
Almost all of Tao's questions begin with what, or why. That forces an open ended response, which is a great way to reduce or eliminate sycophancy and severe hallucinations. The less you steer, the more accurate it gets.
I was simply responding to the point that Anthropic has some altruistic bent and are trying to downplay the fear, when in fact their entire commercial strategy is to convince society that they alone are qualified to hold the keys.
Being in the Bay Area, you can throw a stone and hit a senior employee of these companies, and they will happily gush about the quirks, policies, and intents inside. All the more reason that they are -not- qualified to weigh in on who gets the nuclear codes.
They know what they're doing. It's a playbook. You write scary stuff in the model card to make it look like legitimate whitepaper rEsEarCh, then drip-feed it to the media outlets who make it a headline story. Fear based marketing is the hot trend of the 2020s.
No way. It's simply another layer of abstraction. You don't code in binary, or assembly, or C, or vanilla JavaScript anymore.
Eventually "coding" will simply be prompting skill with the wisdom of architectural decisions.
That's also one way to describe what it's like to code with React et al these days, anyway. Component/hook selection skill with the wisdom of architectural decisions.
> Consoles made sense as a product category where specialized graphics hardware was not generally available for consumer PCs.
This has almost never been true. GPUs existed, and were being used, before the N64.
Your comment also begs the question that the console consumer has transitioned to a gaming pc. They haven't. Gaming PC sales (and hardware) are at all-time lows, except for GPUs, which should probably be renamed to Model Training Units.
I would posit that what we're seeing is a reflection of a content problem, not hardware. Video games have gone the way of Hollywood, with sequels and derivatives, and an uninterested consumer base. People would rather watch a YouTube video of someone playing a video game than play a video game.
One tangible thing this doesn't touch on: SpeechAnalyzer supports streaming, so you can see what it's hearing from you as you talk. A massive UX improvement. Many of the other models force you to record, then it transcribes the audio to text as a single job, then returns the entire blob of text. It's slow, and frustrating if you're talking, only to realize it stopped listening after 2 minutes.
In my experience, the better long-term choice if you're going to vibe code an app is to use Expo.
Its basis is React, so the code output quality is much higher than Swift because there is much more React code in LLM training data.
Everything is in the command line, and debugging is a breeze because it's a web view. But once it's compiled to native iOS, it feels like any other native app.
Expo + Fastlane = fully automated iOS submission and deployment. I issue one command and see a new version in the App Store.
> It's interesting that all models seems to be unbiased out of the box so far
This is really begging the question. If something relies on the perception of a human, it has bias. The data (or lack thereof) used to train models is per se a bias.
The mistake is assuming bias-removal is some virtuous goal to be achieved. It can't, and shouldn't. Alignment, while equally impossible, is at least a goal worth aiming towards.
> Vibe coding is a software development practice assisted by artificial intelligence (AI) where the software developer describes a project or task in a prompt to a large language model (LLM) which generates source code automatically.
Based on this definition, yep, I've been vibe coding since 2023. The products were less sophisticated, and I was copying and pasting one function at a time, but it worked. More important: it was something I couldn't do on my own.
The modern version is that bonafide engineers accept AI-generated code. It's a good thing I'm not a bonafide engineer.