Hacker News Reader

Comment by nicce | Hacker News Reader

> People moan about how badly made Claude code is but Codex seems much worse on every metric

Also, it feels that chatgpt.com and aistudio.google.com are the buggiest websites I have seen for long time. Why it is always something related to LLMs?

View on HN

Because they're the most likely to be 100% vibe coded. And as much as some people still deny it, AI code = buggy code.

All the LLM turds we've curled out at work are the same.

Because LLMs are changing so fast that nobody wants to spend time carefully engineering an efficient setup for them which might just get thrown away in 6 months when the modality changes again.

But are we not told that LLMs are so powerful that nobody would need to spend time to engineer that?

ChatGPT.com is dreadful. The whole thing chokes when the conversation gets moderately long. It's amazing that it's been allowed to stay this way.

I suspect it’s intentional.

Chat sessions are not metered by token usage but rather a fairly high limit of messages per day or something.

The longer chats you have, the more context and token input. So I think that discourages longer chats, and encourages users to start new chats.

It’s actually insane how buggy the Gemini web version is (or at least was a few months ago, since I stopped using it).

It's improved. The scrolling used to be terribly glitchy and would make it difficult to read as text was generated.

But in the same fix, they also removed the reasoning-sample, which kinda sucked.

Reply on news.ycombinator.com