logoalt Hacker News

simonwlast Sunday at 4:38 PM1 replyview on HN

Unfortunately LLMs mostly suck at Swift and SwiftUI from what I've heard - they still change pretty often and as a result there aren't enough fresh examples in the training data.

As primarily a Python/JavaScript programmer I don't have that problem!


Replies

Razenganyesterday at 10:49 AM

They're terrible at anything new, including knowing about THEMSELVES and their latest versions.

This is me asking ChatGPT 5 about ChatGPT 5: https://i.imgur.com/aT8C3qs.png

Asking about Nintendo Switch 2: https://i.imgur.com/OqmB9jG.png

This could be solved and LLMs could be a lot more useful if they could be a wrapper around live web search: Just search for this shit, scrap the top few results, and summarize the info to me.

But that's a stillborn dream, crippled because Google won't let 3rd-party AIs use their search willy nilly and websites don't want to be scrapped :(

Don't get me wrong: I see the potential in AIs/LLMs and I think they could be amazing for everything, but like every awesome thing, they're hampered by corporate (and government) idiocy.

show 1 reply