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

That's silly. Cursor has the best autocomplete experience, period, and some people prefer that to agent-style interactions.

There's still a ton of low hanging fruit that other Copilot-style autocomplete products don't seem to be picking up, like using clipboard contents, identifying the next place in the file to jump to, etc.

I primarily save time coding with AI with autocomplete, followed by chat, with agentic flows a very distant 3rd, so Cursor is a legitimately better product for me.



It’s not silly at all. There is a lot of hyper activity going in terms of social influence.

I didn’t say cursor has poor UX.

I tab too. And use agent for cheaper work I don’t care too much about. That said, the best autocomplete is arguably evolving and cursor does not own that.


I have too much work and too little time. I tried them all and cursor is the only one with a polished enough experience that made it stick right away. Others might be good but I didn’t have anything near the flowless experience of cursor


Someone said "I don't really see why people still use Cursor over tools like Cline / Roo Code"

And your answer is "A lot of power in social influence.", which is a bit silly when autocomplete is the first form of AI assistance a critical mass of people found intuitive + helpful and Cursor has the best implementation of it... meanwhile Cline/Roo Code don't provide it.


You don’t get it - autocomplete is evolving from keyboard clicks to prompts. Tab-ing is not as effective as agentic coding.

Your beloved cursor will go all in on this front, less and less priority on focused cursors in the editor.


You don't get it: what's most effective for me is what's most effective for me.

And it's not "my beloved cursor", not sure why you're being such an absolute weirdo about this.


Nah, you definitely don't get it. Some people are here enjoying the act of programming, and Cursor Tab is acting like an improvement on IntelliSense/autocomplete that actually knows what it's doing. Not all of us want to spend half an hour going back and forth with a robot about what it didn't do quite right when we can be in the actual code, tweak a couple lines, and press tab for it to replicate the change in the next 50 now it knows.

Agentic coding is fine, definitely helps me a lot with setup and boilerplate, but finer business logic details and UX changes are now it's strong suit especially if you know WHAT you want but not HOW to explain it in a clear enough format that it can do it without additional prompting.


I actually like programming, and I find typing and having the model autocomplete my changes pretty useful.

I’d rather do that than painstakingly put my request into prose, cross my fingers, and hope the “agent” doesn’t burn 100,000 tokens making stupid and unrelated changes all over my codebase.

I believe in “show, don’t tell,” and autocomplete is the former while agents are the latter.


> Tab-ing is not as effective as agentic coding.

It is more effective when you have to do a bunch of similar changes. Or when code is standard enough that you just hit tab, and change perhaps one line. Or when parts of code are immediately deduced from context, and substitutions/changes are immediately provided.




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

Search: