That's kind of the whole point of this exercise and my write-up of it.

I'm glad you wrote it up. Thanks! But I feel like the folks behind the HTML5 spec and the comprehensive test suite deserve the lion's share of the credit for this (very neat) achievement.

Most projects don't have a detailed spec at the outset. Decades of experience have shown that trying to build a detailed spec upfront does not work out well for a vast class of projects. And many projects don't even have a comprehensive test suite when they go into production!

Having a comprehensive spec and test suite is an absolute requirement, without it all you got is vibe-testing, LGTM feels. As shown by the OP, you can throw away the code and regenerate it back from tests and specs. Our old manual code is now the new machine code.

I completely agree. I hope I gave them enough credit in the blog post and the GitHub repo.

Yep, and I think it is a great way to draw attention to their work!

In the image they showed for the new one, the mechanic was checking a dipstick...that was still in the vehicle.

I really hope everyone is starting to get disillusioned with OpenAI. They're just charging you more and more for what? Shitty images that are easy to sniff out?

In that case, I have a startup for you to invest in. Its a bridge-selling app.

Haven’t their prices stayed at $20/m for a while now?

They've published anticipated price increases over coming years. Prices will rise dramatically and steadily to meet revenue targets.

AI doesn’t have much of a moat. People can and will easily switch providers.

Sure but there are only a couple leading providers worth considering for coding at least, and there will be consolidation once investment pulls back. They may find a way to collude on raising prices.

Where switching will be easier is with casual chat users plus API consumers that are already using substandard models for cost efficiency. But there will also always be a market for state of art quality.

You have to realize ai is way more trash than you actually give it credit for.

Also with the shoveling of it down the people's throats, more people want authentic human experiences.

>GPT‑5.2 sets a new state of the art across many benchmarks, including GDPval, where it outperforms industry professionals at well-specified knowledge work tasks spanning 44 occupations.

We built a benchmark tool that says our newest model outperforms everyone else. Trust me bro.

>Vibe coding makes me feel dirty in ways that I struggle to articulate precisely. It’s not just that it feels like 'cheating'(though it does). I also think it takes a lot of the fun out of the whole thing.

This exactly. Programming is art, because it comes from the soul. You can tackle a problem a million ways, but there's only one way that YOU would solve it.

Vibe coding feels like people who aren't creative, stealing everyone's creativity, and then morphing it into something they find appealing.

There is no skill.

There is no talent.

You are asking the machine to do ALL THE THINKING. All the little decisions, the quirks, the bugs, the comments to yourself. All the things that make a piece of code unique.

Oh man, that's totally worth $500 Billion dollars and the environmental health of our towns and cities!

Nobody has yet to explain how an LLM can be better than a well paid human expert.

The not needing to pay it well.

A well paid human expert can find lots of uses of LLMs. I'm still not convinced that humans will ever be totally replaced, and what work will look like is human experts using LLMs as another tool in the toolbox, just like how an engineer would have used a slide rule or mechanical calculator back in the day. The kind of work they're good at doesn't cover the full range of necessary engineering tasks, but they do open up new avenues. For instance, yesterday I was able to get the basic gist of three solutions for a pretty complex task in about an hour. The result of that was me seeing that two of them were unlikely to work for what I'm doing, so that now I can invest actual effort in the third solution.

Tools can make individuals and teams more effective. This is just as true for LLM-based tools as it was for traditional ones.

The question is not whether one (1) LLM can replace one (1) expert.

Rather, it is how much farther an expert can get through better tooling. In my experience, it can be pretty far indeed.

Every other day its "China creates a breakthrough that was never thought possible" and "America shits in hand; Claps."

At least in this case it's somewhat sensationalized because the US did this in the 1950’s and concluded that it was more economical and simpler to use mined Uranium instead of breeding with Thorium.

You should not be feeding your medical records into ChatGPT.

And you shouldn't be using Gmail or Google Search. At some point the benefits outweigh the costs.

How does an email service compare to a glorified if-then machine that hordes all your data?

Why not?

I can imagine a few different reasons you might have, but I don't want to guess.

Anti-AI bias is motivated by the waste of natural resources due to a handful of non-technical douchebag tech bros.

Everything isn't about money, I know that status and power are all you ai narcissists dream about. But you'll never be Bill Gates, nor will you be Elon Musk.

Once ai has gone the way of "Web3", "NFTs", "blockchain", "3D tvs", etc; You'll find a new grift to latch your life savings onto.