Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

>Maybe gpt-4 would've made fewer errors?

Likely. There's a big gap between them. I don't really use 3.5 anymore even though it costs money.



You should use bing. It’s chatgpt-4 and it’s miles better than chatgpt-3. Bing even searches the web for answers.

My only issue with being is that it’s extremely sensitive and will end a conversation for the most ridiculous things. But it’s still well worth it if you’re prepared to deal with its pettiness & stubbornness.

I’ve been using it to help me figure out React hooks (I’ve only used class-based react) and it’s REALLY good. It even warns you of bad practices.

It’s also pretty accurate at giving me a specific tailwind class. It’s much quicker than browsing the docs.


I actually hate the other cloud LLMs like bing and bard

their current implementation isn't as like a person typing

It makes me appreciate the finishing touches on the ChatGPT UX

I wonder how much of a factor that is for other people


So I was trying out the new copilot built into the latest update of windows 11. Compared the same question and output with chatgpt with gpt 4 and copilot. The answers were almost the same. Only difference is the UI for copilot on windows 11 is just downright awful. The panel docks to the right side of the screen , takes up about a quarter of the desktop in this vertical narrow window thats not even resizable. So yeah I agree, the OpenAI built UI for chatgpt is still better than anything microsoft or even google has put out there to augment their search engine.


You can also use web.skype.com and add bing as a contact. This gives you a much cleaner UI


This is interesting. Indeed it is much cleaner UI. Thanks for sharing.




Consider applying for YC's Winter 2026 batch! Applications are open till Nov 10

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: