🎓 ASU public interest tech grad student
🎵 least musically successful member of my high school band
| Website | https://dou.glass |
| Location | Houston-ish |
| Pronouns | He/Him |
| Website | https://dou.glass |
| Location | Houston-ish |
| Pronouns | He/Him |
RE: https://mastodon.social/@stroughtonsmith/116030136026775832
This is one of the worst takes from LLM enthusiasts.
Compilers are deterministic, extremely well tested, made out of incredibly detailed specifications debated for months and properly formalized.
LLMs are random content generators with a whole lot of automatically trained heuristics. They can produce literally anything. Not a single person who built them can predict what the output will be for a given input.
Comparing both is a display of ignorance and dishonesty.
I just spent an hour working on some form validation CSS to wait until after user interaction had occurred, only to discover after deeper reading that the :user-(in)valid pseudo selectors already do this.
And that's why you should always read the docs.