The tweet I saw a few weeks ago about LLMs enabling building stupid ideas that would have never been built otherwise particularly resonates with this one.
Crystal ball, maybe, but 3 years ago, the AI generated classes with empty methods containing "// implement logic here" and now, AI is generating whole stack applications that run from the first try.
Past performance does not guarantee future results, of course. But acting like AI is now magically going to stagnate is also a really bold bet.
> now, AI is generating whole stack applications that run from the first try
I sincerely doubt that, because it still can't even generate a few hundred line script that runs on the first try. I would know, I just tried yesterday. The first attempt was using hallucinated APIs and while I did get it to work eventually, I don't think it can one shot a complex application if it can't one shot a simple script.
IMO, AI has already stagnated and isn't significantly better than it was 3 years ago. I don't see how it's supposed to get better still when the improvement has already stopped.
I routinely generate applications for my personal use using OpenCode + Claude Sonnet/Opus.
Yesterday I generated an app for my son to learn multiplication tables using spaced repetition algorithm and score keeping. It took me like 5 minutes.
Of course if you use ChatGPT it will not work but there is no way Claude Code/Open Code with any modern model isn't able to generate a one hundred line script on the first try.
I was asking which tool, not which, not which model.
For the same model, you can just have it generate dad jokes or use it in a tool like OpenCode or Cursor or Zed or Cline or … and make it program complex things.
If I use Claude Sonnet on duck.ai I will have hard time generating something interesting. The same model in OpenCode does all my programming work.
I mean, the person above complaining about it not being able to create a simple thing is absolutely holding them wrong! They aren’t feeding the right context, aren’t using the correct tools or harnesses, who knows. But the problem exists between keyboard and chair, so to speak.
I’m constantly amazed at the amount of scope I can now one-shot with Claude Code. It can crank out multi command cli apps with almost zero hand holding beyond telling what to generate… you know, the hard part. And then we’ll back and forth to refine the working thing it built.
>isn't significantly better than it was 3 years ago.
Eh?
Ever hear the saying the first 90% of a problem is 90% of the work, the last 10% of the program is also 90% of the work.
AI/LLMs have improved massively in that context. That's not even including the other model types such as visual/motion-visual/audio which are to the point that telling their output from reality is a chore.
And one shotting a simple script simply doesn't mean much without context. I have it dump relatively complex powershell scripts often enough and it's helped me a lot with being able to explain scripting actions to other humans where before I'd make assumptions about the other users knowledge where it was not warranted.
The biggest grift is invested tech Bro's trying to sell you on thr fact that Ai growth is linear or even exponential.
In reality it's Logarithmic. Maybe with the occasional jolt. You'd think with Moores "law" that we'd know better by now that explosive growth isn't forever. Or at least that we're bound to physics as a cap to hit.
Really? Because this perfectly explains why it will never replace them: it needs an exact language listing everything required to function as you expect it.
I'm native French and nobody would consider code countable. "codes" makes no sense. We'd talk about "lines of code" as a countable in French just like in English.
Codes is a proper grammatical word in English, but we don’t use it in reference to general computer programming.
You can for example have two different organizations with different codes of conduct.
There is though nothing technically wrong with seeing each line of code as an complete individual code and referring to then multiple of them as codes.
The number one solution is obvious and I don't know why nobody talks about it: mandate work from home whenever possible.
Daily commute represents 20% of CO2 emissions, it's an insanely high number, and it has an incredibly easy, already tested thanks to COVID, solution.
People will say "but what about the shops that will close". They won't, they will relocate in residential neighborhoods where people now live AND work.
All the potential issues people might raise actually disappear as WFH becomes the new normal and not a potentially temporary state like it was during COVID.
Even if only 50% of jobs can be done from home, that's an instant 10% reduction JUST from commute. But in reality it'll lead to a much larger decrease, with less spending on fast-fashion, more proximity businesses, etc.
Isn't Shanghai a Tier 1 city? IMO it's not very representative of the whole country.
It's also not like China is an overachieving outlier, but western nations actively having been sabotaged by its leadership at least since 1990 and MUCH MUCH more so since occupy wallstreet.
FFS Germany is blowing up its nuclear powerplants on a never before seen record breaking schedule so that a potential successor government cant reactivate them.
Interesting, never heard anyone calling some place a Tier 1.5 city. Is this a recent development as "almost official" as the Tiers itself, something obvious I just never picked up on or people taking pride in their Tier 2s doing really well?
Also why does the Tier list keep expanding downwards? Wasn't being called a Tier 4 basically exclusively an insult? Sub culture not being satisfied with just embracing rotting anymore, but now racing for the bottom of the sea?
It’s simple, you use innerHTML if you know for sure where the input comes from and if it’s safe (for example when you define it as a hard coded string in your own code).
You use setHTML when you need to render HTML that is potentially unsafe (for example forum posts or IM messages). Honest question, which part of that isn’t clear?
How is adding an element to the parent the same as replacing all the content of the element? You guys are exhausting. Think a bit before spouting nonsense?
reply