211–220 of 410 posts
Plus its less about the actual code generation and more about how to use it effectively. I wrote a simple piece on how I use it to automate the boring parts of dev work to great effect https://quickthoughts.ca/posts/automate-smarter-maximizing-r...)
I'm with Cursor for the simple reason it is in practice unlimited. Honestly the slow requests after 500 per month are fast enough. Will I stay with Cursor? No, ill switch the second something better comes along.
I'm cursor with claude 3.7 Somehow other models don't work as well with it. ,,auto'' is the worst. Still, I hate it when it deletes all my unit tests to ,,make them pass''
Or, my favorite: when you’ve been zeroing in on something actually interesting and it says at the last minute, “let’s simplify our approach”. It then proceeds to rip out all the code you’ve written for the last 15 minutes and insert a trivial simulacrum of the feature you’ve been working on that does 2% of what you originally specified.
$5 to anyone who can share a rules.md file that consistently guides Sonnet 3.7 to give up and hand back control when it has no idea what it’s doing, rather than churn hopelessly and begin slicing out nearby unrelated code like it’s trying to cut out margins around a melanoma.
Zed. They've upped their game in the AI integration and so far it's the best one I've seen (external from work). Cursor and VSCode+Copilot always felt slow and janky, Zed is much less janky feels like pretty mature software, and I can just plug in my Gemini API key and use that for free/cheap instead of paying for the editor's own integration.
Zed doesn't even run on my system and the relevant github issue is only updated by people who come to complain about the same issue.
Neither? I'm surprised nobody has said it yet. I turned off AI autocomplete, and sometimes use the chat to debug or generate simple code but only when I prompt it to. Continuous autocomplete is just annoying and slows me down.
Zed. They've upped their game in the AI integration and so far it's the best one I've seen (external from work). Cursor and VSCode+Copilot always felt slow and janky, Zed is much less janky feels like pretty mature software, and I can just plug in my Gemini API key and use that for free/cheap instead of paying for the editor's own integration.
Does it have Cursor’s “tab” feature?
Earlier quoted context omitted.
Cursor/Windsurf and similar IDEs and plugins are more than autocomplete on steroids. Sure, you might not like it and think you as a human should write all code, but frequent experience in the industry in the past months is that productivity in the teams using tools like this has greatly increased. It is not unreasonable to think that someone deciding not to use tools like this will not be competitive in the market in…
https://alex.party/posts/2025-05-05-the-future-of-web-develo...
A lot of people are against change because it endangers their routine, way of working, livelihood, which might be a normal reaction. But as accountants switched to using calculators and Excel sheets, we will also switch to new tools.
Earlier quoted context omitted.
Approximately how much does it cost in practice to use Aider? My understanding is that Aider itself is free, but you have to pay per token when using an API key for your LLM of choice. I can look up for myself the prices of the various LLMs, but it doesn't help much, since I have no intuition whatsoever about how many tokens I am likely to consume. The attraction of something like Zed or Cursor for me is that I just…
I'm using Gemini 2.5 Pro with Aider and Cline for work. I'd say when working for 8 full hours without any meetings or other interruptions, I'd hit around $2. In practice, I average at $0.50 and hit $1 once in the last weeks.
Copilot at work and Junie at home. I found nothing about my VSCode excursions to be better than Sublime or IntelliJ.
Earlier quoted context omitted.
Why should the Emacs community care whether someone decides to build a custom editor with AI features? If anything this would bring more interest and development into the ecosystem, which everyone would benefit from. Anyone not interested can simply ignore it, as we do for any other feature someone implements into their workflow.
what i find interesting is why is nobody building llms trained on using the shell and PTY at its full right now its dumb unix piping only I want an AI that can use emacs or vim with me
Which is exactly why it hasn’t been commercially developed.
Earlier quoted context omitted.
what i find interesting is why is nobody building llms trained on using the shell and PTY at its full right now its dumb unix piping only I want an AI that can use emacs or vim with me
There are tens (maybe low hundreds?) of thousands of people who want that. Which is exactly why it hasn’t been commercially developed.
I was exploring using andyk/ht discussed on hn a few months back, to sit as a proxy my llm can call at the same time i control via xtermjs, but i need to figure out how to train the llm to output keybindings/special keys etc, but promising start nonetheless, i can indeed parse a lot of extra info than just a command, just imagine if AI could use all of the shell auto-complete features but feed into it..
maybe i should revisit/cleanup that repo and make it public. It feels like with just some data training on special key bindings etc an llm should be able to type, even if -char by char- at a faster speed than a human, to control TUI's