Earlier quoted context omitted.
Saved you a click: user: christophilus created: October 16, 2014 karma: 11683
Interesting that karma points can dispel such doubts. I presume there is no market for hn influencers?
Cursor 1.0
351–360 of 492 posts
Re: Cursor 1.0
#352Recently canceled cursor. I think there's a shift happening right now with the improvements in the ability to process large context sizes and stay on task: Traditional code editing -> autocomplete -> file editing -> agent mode This is basically a gradient of AI output sizes. Initially, with the ability to generate small snippets (autocomplete), and moving up to larger and larger edits across the codebase. Cursor repr…
Re: Cursor 1.0
#353Re: Cursor 1.0
#354As someone who has two annual subs of Cursor Pro (one from student account and another from Lenny's newsletter), I just spent $100 on Claude Code and I haven't touched Cursor AI for any coding tasks since. If you already spend anything near or over $100 on Cursor, it's no brainer. The agent experience is night and day. No more wrong tool-calling, premature ending of conversation, failure to apply changes or overwriti…
I think the focus on Cursor Agent is misplaced. I always turn to Ask and find it annoying they keep reverting it to Agent any time I'm not looking.
Re: Cursor 1.0
#355I trust that Claude Code is good, and I believe that most people commenting here are truthful to their experiences. However, I have a strange feeling that companies are using bots on these announcements comments. Maybe I'm being overcautious, but one of the worst things (for me) that came from the AI rush of these past years is this feeling that everything is full of bots. I know that people have preferences, but I f…
Re: Cursor 1.0
#356Earlier quoted context omitted.
> It's like the cheap Ubers of yesteryear. Inference cost is plummeting. It’s like the cheap Ubers of yesteryear, if the cost of hiring a driver dropped by a factor of a thousand in the past three years .
You forgot the cost of training (which is zero for Uber drivers, but far from zero for Cursor)
Re: Cursor 1.0
#357Earlier quoted context omitted.
I've been getting rate limit errors with Zed (using my own Claude API) while the same query will work in Claude Code. So still some rough edges there.
I pay that 20€ a month for a subscription, and the claude opus thinking model from Zed is really solid now. Had similar issues earlier, now it works. Also it's great that I do not need to use the vscode ecosystem. Zed is snappy, has a great UI and now a good assistant too.
Re: Cursor 1.0
#358I trust that Claude Code is good, and I believe that most people commenting here are truthful to their experiences. However, I have a strange feeling that companies are using bots on these announcements comments. Maybe I'm being overcautious, but one of the worst things (for me) that came from the AI rush of these past years is this feeling that everything is full of bots. I know that people have preferences, but I f…
Re: Cursor 1.0
#359As someone who has two annual subs of Cursor Pro (one from student account and another from Lenny's newsletter), I just spent $100 on Claude Code and I haven't touched Cursor AI for any coding tasks since. If you already spend anything near or over $100 on Cursor, it's no brainer. The agent experience is night and day. No more wrong tool-calling, premature ending of conversation, failure to apply changes or overwriti…
Re: Cursor 1.0
#360Recently canceled cursor. I think there's a shift happening right now with the improvements in the ability to process large context sizes and stay on task: Traditional code editing -> autocomplete -> file editing -> agent mode This is basically a gradient of AI output sizes. Initially, with the ability to generate small snippets (autocomplete), and moving up to larger and larger edits across the codebase. Cursor repr…