Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Cursor CLI

cursor.com

Post reply on HN
Print view View original

261–270 of 275 posts

Re: Cursor CLI

#261

Post by centphe »

gpeal wrote: post #144
LeafItAlone wrote: post #124

Earlier quoted context omitted.

I find the Codex CLI to be the worst of the CLI tools I’ve used (including, but not limited to, Claude Code, Gemini, Aider). There’s something about it that makes it clunky. Haven’t tried Cursor CLI yet though.

We (Codex) shipped a pretty large CLI update today and have many more improvements coming. Give it a try if you haven't. https://x.com/OpenAIDevs/status/1953559797883891735 (0.19 now)

I was actually eager to try it today, but it've just failed with some issue which is open since July 8 (https://github.com/openai/codex/issues/1481) and I gave up on it.

Re: Cursor CLI

#262

Post by worldsayshi »

ricericerice wrote: post #258
apwell23 wrote: post #233

Earlier quoted context omitted.

yes i am rejigging my whole vim setup Following are now stars of my workflow * Git plugins - Diffview, gitsigns, fugitive * Claude Code plugin / Terminals with claude code * Neovim sessions * Git worktrees Editing focused workflows have taken an backseat * LSP * Vim motion and editing efficiency * File navigation * Layouts

why even use vim at this point? the LLM ecosystem there is decent, but definitely less polished than using a modern IDE

Vim motions are nice.

Re: Cursor CLI

#263

Post by CubicalBatch »

computerfriend wrote: post #211
sneak wrote: post #53

Earlier quoted context omitted.

When they stop getting desperate for differentiation by spamming their brand advertising in your repo against your will. Claude Code likes to add "attribution" in commit messages, which is just pure spam.

I've experimented a little with LLM agents (only Claude Code). I definitely don't want the agent to write the commit messages (they should be written by a human as they're for human consumption) so I manually added the co-author trailer. It's morally correct to provide attribution.

I find LLM written commits are more often than not better than humans one

Re: Cursor CLI

#265

Post by sunnybeetroot »

SwiftyBug wrote: post #220
kridsdale3 wrote: post #67

Earlier quoted context omitted.

Xcode pretty much hung up their hat this year, and threw in with Claude.

What do you mean? I've been patiently waiting for the death of Xcode for a long time. Do you think it's near?

No idea what the user meant, Xcode is releasing IDE AI this year

Re: Cursor CLI

#266

Post by _betty_ »

eagerpace wrote: post #125

I really like the IDE. It makes enough mistakes that I need to be constantly testing and catching little errors. I’ll interrupt the flow often when it’s going down a path I don’t want it to. When using Codex, for example, it’s doing too much in the background that is harder to correct afterwards. Am I doing this wrong?

I like that I can use the ide while a cli is working, keep an eye on git changes and interrupt where needed.

I find in ide they like opening documents/changing tabs too much and it means j can't do other things.

Re: Cursor CLI

#268

Post by sofal »

thornewolf wrote: post #42

They realized that CLI is the much better interface for these kinds of tasks.

I don't think this is why. I listened to a recent podcast with Michael Truell and he made clear they think the TUI is an inferior form factor. This feels more like a reactionary move than a visionary one.

Re: Cursor CLI

#269

Post by sneak »

computerfriend wrote: post #211
sneak wrote: post #53

Earlier quoted context omitted.

When they stop getting desperate for differentiation by spamming their brand advertising in your repo against your will. Claude Code likes to add "attribution" in commit messages, which is just pure spam.

I've experimented a little with LLM agents (only Claude Code). I definitely don't want the agent to write the commit messages (they should be written by a human as they're for human consumption) so I manually added the co-author trailer. It's morally correct to provide attribution.

Code is also for human consumption.

SICP contains the famous quote: “Programs must be written for people to read, and only incidentally for machines to execute.”

Re: Cursor CLI

#270

Post by eru »

yunohn wrote: post #212
eru wrote: post #170

Earlier quoted context omitted.

Whether Claude and co understand is probably not a great proxy for whether your docs are good for humans.

Hmmm, in my experience if something like documentation confuses the current SOTA LLMs, then it will confuse the average developer for sure.

I had the other direction in mind: you can put together some text that the average LLM will figure out, but that will be really annoying for your average developer.

Eg if you write your instructions in a mixture of base 64, traditional Chinese, morse code and Polish, the LLM will still figure it out.

Post reply on HN