I kinda feel this bench-marking thing with Chinese models is like university Olympiads, they specifically study for those but when time comes for the real world work they seriously lack behind.

I kinda feel like the goalposts are shifting. While we're not there yet, in a world where Chinese models surpass Western ones, HN will be nitpicking edge cases long after the ship sails

I don’t think it’s undermining the effort and improvement, but usability of these models aren’t usually what their benchmarks suggest.

Last time there was a hype about GLM coding model, I tested it with some coding tasks and it wasn’t usable when comparing with Sonnet or GPT-5

I hope this one is different

the system works for several days, weeks or months before a bug happens to surface it is complete nonsense not those you missed something simple bugs, it is deep within the infrastructure of your system, you call your friend to cancel that event you were planing only to find out he is also wrestling with a sudden bug, you bang your head but can't solve it, the next day you compile the project and it works again. if astrology can't explain this I don't know what can?

although our internet is whitelist-blocked and I can only read the comments here, this reminds me of something my friend said some years ago, he said my car is the extension of my limbs and I can feel the limits of my car similar to my hands and feet

the move don't have to be permanent, there are alternatives and as we increase our usage and give active feedback and commit to invest even little money in them, they will improve too. I've seen this pattern a thousand times the monopoly gets worst and worst until a revolutionary new tech will rise it applies to social concepts, business sectors, companies, mother-in-laws, etc.

Just WOW

but doing that would you not end up with less than vscode?

using graphql specifically Apollo was one of my regrettable decisions when I was designing a system 3 years ago, one that haunts me still today with wired bugs, too much effort to upgrade the version while prev version still have bugs etc. and I lost performance and simplicity of rest on top of that

It’s one of the best pieces of software I’ve worked with. I guess simplicity is in the eye of the beholder :)

It took me a while to learn the "right way" of doing Apollo. An alternative like Relay is much more opinionated so perhaps that would've helped me get there faster. But I eventually came around and now I agree that Apollo is an incredible piece of technology. I later worked on a REST API and found myself wanting to recreate much of Apollo. Especially the front-end caching layer.

exactly my experience, suddenly thousands of non indexed pages, never figured out why, had to disband the business as it was content website selling ads.

Good riddance.

now I don't have clients and I'm poor :(

Will I ever be able to learn the Fourier transform?

Yes! Step 1 is forgetting about the name so it doesn't feel as daunting.

Disclaimer: I've not actually done step 1, but I have more faith in you than in myself.

Had I known this I would not have built my own solution